04/29/2020 12:09:03 MainProcess     MainThread      logger          log_setup                 INFO     Log level set to: TRACE
04/29/2020 12:09:03 MainProcess     MainThread      launcher        execute_script            DEBUG    Executing: convert. PID: 15336
04/29/2020 12:09:05 MainProcess     MainThread      launcher        _test_for_tf_version      DEBUG    Installed Tensorflow Version: 1.15
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   __init__                  DEBUG    Initializing QueueManager
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   __init__                  DEBUG    Initialized QueueManager
04/29/2020 12:09:05 MainProcess     MainThread      convert         __init__                  DEBUG    Initializing Convert: (args: Namespace(alignments_path='D:\\Testing\\faceswap\\Extract\\Source\\source_test1\\source_test1\\alignments.fsa', allow_growth=False, colab=False, color_adjustment='avg-color', configfile=None, filter=None, frame_ranges=None, func=<bound method ScriptExecutor.execute_script of <lib.cli.launcher.ScriptExecutor object at 0x00000260EB9D09C8>>, gpus=1, input_aligned_dir=None, input_dir='D:\\Testing\\faceswap\\Extract\\Source\\source_test1', jobs=0, keep_unchanged=False, logfile='D:\\Testing\\faceswap\\Extract\\log_test1.log', loglevel='TRACE', mask_type='none', model_dir='D:\\Testing\\faceswap\\Extract\\Model\\model_test1', nfilter=None, on_the_fly=False, output_dir='D:\\Testing\\faceswap\\Extract\\Convert\\test2', output_scale=100, redirect_gui=True, ref_threshold=0.4, reference_video=None, scaling='none', singleprocess=False, swap_model=False, trainer=None, writer='opencv'))
04/29/2020 12:09:05 MainProcess     MainThread      image           __init__                  DEBUG    Initializing ImagesLoader: (path: D:\Testing\faceswap\Extract\Source\source_test1, queue_size: 8, fast_count: True, skip_list: None, count: None)
04/29/2020 12:09:05 MainProcess     MainThread      image           __init__                  DEBUG    Initializing ImagesLoader: (path: D:\Testing\faceswap\Extract\Source\source_test1, queue_size: 8, args: None)
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager getting: 'ImagesLoader'
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   add_queue                 DEBUG    QueueManager adding: (name: 'ImagesLoader', maxsize: 8)
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   add_queue                 DEBUG    QueueManager added: (name: 'ImagesLoader')
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager got: 'ImagesLoader'
04/29/2020 12:09:05 MainProcess     MainThread      image           _check_for_video          DEBUG    Input 'D:\Testing\faceswap\Extract\Source\source_test1' is_video: False
04/29/2020 12:09:05 MainProcess     MainThread      image           _get_fps                  DEBUG    25.0
04/29/2020 12:09:05 MainProcess     MainThread      utils           get_image_paths           DEBUG    Scanned Folder contains 2 files
04/29/2020 12:09:05 MainProcess     MainThread      utils           get_image_paths           TRACE    Scanned Folder Contents: [<DirEntry 'source_test1'>, <DirEntry 'alignments.fsa'>]
04/29/2020 12:09:05 MainProcess     MainThread      utils           get_image_paths           DEBUG    Returning 0 images
04/29/2020 12:09:05 MainProcess     MainThread      image           _get_count_and_filelist   DEBUG    count: 0
04/29/2020 12:09:05 MainProcess     MainThread      image           _get_count_and_filelist   TRACE    filelist: []
04/29/2020 12:09:05 MainProcess     MainThread      fsmedia         __init__                  DEBUG    Initializing Alignments: (is_extract: False, input_is_video: False)
04/29/2020 12:09:05 MainProcess     MainThread      fsmedia         _set_folder_filename      DEBUG    Alignments File provided: 'D:\Testing\faceswap\Extract\Source\source_test1\source_test1\alignments.fsa'
04/29/2020 12:09:05 MainProcess     MainThread      fsmedia         _set_folder_filename      DEBUG    Setting Alignments: (folder: 'D:\Testing\faceswap\Extract\Source\source_test1\source_test1' filename: 'alignments.fsa')
04/29/2020 12:09:05 MainProcess     MainThread      alignments      __init__                  DEBUG    Initializing Alignments: (folder: 'D:\Testing\faceswap\Extract\Source\source_test1\source_test1', filename: 'alignments.fsa')
04/29/2020 12:09:05 MainProcess     MainThread      serializer      get_serializer            DEBUG    <lib.serializer._PickleSerializer object at 0x00000260F474B288>
04/29/2020 12:09:05 MainProcess     MainThread      serializer      get_serializer            DEBUG    <lib.serializer._CompressedSerializer object at 0x00000260F44BF048>
04/29/2020 12:09:05 MainProcess     MainThread      alignments      _get_location             DEBUG    Getting location: (folder: 'D:\Testing\faceswap\Extract\Source\source_test1\source_test1', filename: 'alignments.fsa')
04/29/2020 12:09:05 MainProcess     MainThread      alignments      _get_location             DEBUG    Valid Alignments filename provided: 'alignments.fsa'
04/29/2020 12:09:05 MainProcess     MainThread      alignments      _get_location             VERBOSE  Alignments filepath: 'D:\Testing\faceswap\Extract\Source\source_test1\source_test1\alignments.fsa'
04/29/2020 12:09:05 MainProcess     MainThread      alignments      have_alignments_file      TRACE    True
04/29/2020 12:09:05 MainProcess     MainThread      alignments      _load                     DEBUG    Loading alignments
04/29/2020 12:09:05 MainProcess     MainThread      alignments      have_alignments_file      TRACE    True
04/29/2020 12:09:05 MainProcess     MainThread      alignments      _load                     INFO     Reading alignments from: 'D:\Testing\faceswap\Extract\Source\source_test1\source_test1\alignments.fsa'
04/29/2020 12:09:05 MainProcess     MainThread      serializer      load                      DEBUG    filename: D:\Testing\faceswap\Extract\Source\source_test1\source_test1\alignments.fsa
04/29/2020 12:09:05 MainProcess     MainThread      serializer      load                      DEBUG    stored data type: <class 'bytes'>
04/29/2020 12:09:05 MainProcess     MainThread      serializer      unmarshal                 DEBUG    data type: <class 'bytes'>
04/29/2020 12:09:05 MainProcess     MainThread      serializer      unmarshal                 DEBUG    returned data type: <class 'dict'>
04/29/2020 12:09:05 MainProcess     MainThread      serializer      load                      DEBUG    data type: <class 'dict'>
04/29/2020 12:09:05 MainProcess     MainThread      alignments      _load                     DEBUG    Loaded alignments
04/29/2020 12:09:05 MainProcess     MainThread      alignments      _has_legacy_structure     DEBUG    legacy structure: False
04/29/2020 12:09:05 MainProcess     MainThread      alignments      _has_legacy_landmarksxy   DEBUG    checking legacy landmarksXY
04/29/2020 12:09:05 MainProcess     MainThread      alignments      _has_legacy_landmarksxy   DEBUG    legacy landmarksXY: False
04/29/2020 12:09:05 MainProcess     MainThread      alignments      _has_legacy_landmarks_list DEBUG    checking legacy landmarks as list
04/29/2020 12:09:05 MainProcess     MainThread      alignments      __init__                  DEBUG    Initialized Alignments
04/29/2020 12:09:05 MainProcess     MainThread      fsmedia         __init__                  DEBUG    Initialized Alignments
04/29/2020 12:09:05 MainProcess     MainThread      convert         __init__                  DEBUG    Initializing OptionalActions
04/29/2020 12:09:05 MainProcess     MainThread      convert         _remove_skipped_faces     DEBUG    Filtering Faces
04/29/2020 12:09:05 MainProcess     MainThread      convert         _get_face_hashes          VERBOSE  Aligned directory not specified. All faces listed in the alignments file will be converted
04/29/2020 12:09:05 MainProcess     MainThread      convert         _remove_skipped_faces     DEBUG    No face hashes. Not skipping any faces
04/29/2020 12:09:05 MainProcess     MainThread      convert         __init__                  DEBUG    Initialized OptionalActions
04/29/2020 12:09:05 MainProcess     MainThread      convert         _queue_size               DEBUG    32
04/29/2020 12:09:05 MainProcess     MainThread      convert         _add_queues               DEBUG    Adding queues. Queue size: 32
04/29/2020 12:09:05 MainProcess     MainThread      convert         _queue_size               DEBUG    32
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   add_queue                 DEBUG    QueueManager adding: (name: 'convert_in', maxsize: 32)
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   add_queue                 DEBUG    QueueManager added: (name: 'convert_in')
04/29/2020 12:09:05 MainProcess     MainThread      convert         _queue_size               DEBUG    32
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   add_queue                 DEBUG    QueueManager adding: (name: 'convert_out', maxsize: 32)
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   add_queue                 DEBUG    QueueManager added: (name: 'convert_out')
04/29/2020 12:09:05 MainProcess     MainThread      convert         _queue_size               DEBUG    32
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   add_queue                 DEBUG    QueueManager adding: (name: 'patch', maxsize: 32)
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   add_queue                 DEBUG    QueueManager added: (name: 'patch')
04/29/2020 12:09:05 MainProcess     MainThread      convert         __init__                  DEBUG    Initializing DiskIO: (alignments: <scripts.fsmedia.Alignments object at 0x00000260F46DB048>, images: <lib.image.ImagesLoader object at 0x00000260F4446448>, arguments: Namespace(alignments_path='D:\\Testing\\faceswap\\Extract\\Source\\source_test1\\source_test1\\alignments.fsa', allow_growth=False, colab=False, color_adjustment='avg-color', configfile=None, filter=None, frame_ranges=None, func=<bound method ScriptExecutor.execute_script of <lib.cli.launcher.ScriptExecutor object at 0x00000260EB9D09C8>>, gpus=1, input_aligned_dir=None, input_dir='D:\\Testing\\faceswap\\Extract\\Source\\source_test1', jobs=0, keep_unchanged=False, logfile='D:\\Testing\\faceswap\\Extract\\log_test1.log', loglevel='TRACE', mask_type='none', model_dir='D:\\Testing\\faceswap\\Extract\\Model\\model_test1', nfilter=None, on_the_fly=False, output_dir='D:\\Testing\\faceswap\\Extract\\Convert\\test2', output_scale=100, redirect_gui=True, ref_threshold=0.4, reference_video=None, scaling='none', singleprocess=False, swap_model=False, trainer=None, writer='opencv'))
04/29/2020 12:09:05 MainProcess     MainThread      fsmedia         __init__                  DEBUG    Initializing PostProcess
04/29/2020 12:09:05 MainProcess     MainThread      fsmedia         _get_items                DEBUG    Postprocess Items: {}
04/29/2020 12:09:05 MainProcess     MainThread      fsmedia         __init__                  DEBUG    Initialized PostProcess
04/29/2020 12:09:05 MainProcess     MainThread      convert         _get_frame_ranges         DEBUG    No frame range set
04/29/2020 12:09:05 MainProcess     MainThread      convert         _get_writer               DEBUG    Writer args: ['D:\\Testing\\faceswap\\Extract\\Convert\\test2']
04/29/2020 12:09:05 MainProcess     MainThread      plugin_loader   _import                   INFO     Loading Writer from Opencv plugin...
04/29/2020 12:09:05 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing Writer: (output_folder: 'D:\Testing\faceswap\Extract\Convert\test2')
04/29/2020 12:09:05 MainProcess     MainThread      config          __init__                  DEBUG    Initializing: Config
04/29/2020 12:09:05 MainProcess     MainThread      config          get_config_file           DEBUG    Config File location: 'D:\Testing\faceswap\config\convert.ini'
04/29/2020 12:09:05 MainProcess     MainThread      _config         set_defaults              DEBUG    Setting defaults
04/29/2020 12:09:05 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'color']
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: color_transfer_defaults.py, module_path: plugins.convert.color, plugin_type: color
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.color.color_transfer_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'color.color_transfer', info: 'Options for transfering the color distribution from the source to the target image using the mean and standard deviations of the L*a*b* color space.\nThis implementation is (loosely) based on the 'Color Transfer between Images' paper by Reinhard et al., 2001. matching the histograms between the source and destination faces.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.color_transfer', title: 'clip', datatype: '<class 'bool'>', default: 'True', info: 'Should components of L*a*b* image be scaled by np.clip before converting back to BGR color space?\nIf False then components will be min-max scaled appropriately.\nClipping will keep target image brightness truer to the input.\nScaling will adjust image brightness to avoid washed out portions in the resulting color transfer that can be caused by clipping.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: method)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.color_transfer', title: 'preserve_paper', datatype: '<class 'bool'>', default: 'True', info: 'Should color transfer strictly follow methodology layed out in original paper?\nThe method does not always produce aesthetically pleasing results.\nIf False then L*a*b* components will be scaled using the reciprocal of the scaling factor proposed in the paper. This method seems to produce more consistently aesthetically pleasing results.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: method)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: color.color_transfer
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: manual_balance_defaults.py, module_path: plugins.convert.color, plugin_type: color
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.color.manual_balance_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'color.manual_balance', info: 'Options for manually altering the balance of colors of the swapped face')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'colorspace', datatype: '<class 'str'>', default: 'HSV', info: 'The colorspace to use for adjustment: The three adjustment sliders will effect the image differently depending on which colorspace is selected:\n	 RGB: Red, Green, Blue. An additive colorspace where colors are obtained by a linear combination of Red, Green, and Blue values. The three channels are correlated by the amount of light hitting the surface. In RGB color space the color information is separated into three channels but the same three channels also encode brightness information.\n	 HSV: Hue, Saturation, Value. Hue - Dominant wavelength. Saturation - Purity / shades of color. Value - Intensity. Best thing is that it uses only one channel to describe color (H), making it very intuitive to specify color.\n	 LAB: Lightness, A, B. Lightness - Intensity. A - Color range from green to magenta. B - Color range from blue to yellow. The L channel is independent of color information and encodes brightness only. The other two channels encode color.\n	 YCrCb: Y - Luminance or Luma component obtained from RGB after gamma correction. Cr - how far is the red component from Luma. Cb - how far is the blue component from Luma. Separates the luminance and chrominance components into different channels.', rounding: 'None', min_max: None, choices: ['RGB', 'HSV', 'LAB', 'YCrCb'], gui_radio: True, fixed: True, group: color balance)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'balance_1', datatype: '<class 'float'>', default: '0.0', info: 'Balance of channel 1:\n	RGB: Red\n	HSV: Hue\n	LAB: Lightness\n	YCrCb: Luma', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: color balance)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'balance_2', datatype: '<class 'float'>', default: '0.0', info: 'Balance of channel 2:\n	RGB: Green\n	HSV: Saturation\n	LAB: Green > Magenta\n	YCrCb: Distance of red from Luma', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: color balance)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'balance_3', datatype: '<class 'float'>', default: '0.0', info: 'Balance of channel 3:\n	RGB: Blue\n	HSV: Intensity\n	LAB: Blue > Yellow\n	YCrCb: Distance of blue from Luma', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: color balance)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'contrast', datatype: '<class 'float'>', default: '0.0', info: 'Amount of contrast applied.', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: brightness contrast)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'brightness', datatype: '<class 'float'>', default: '0.0', info: 'Amount of brighness applied.', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: brightness contrast)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: color.manual_balance
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: match_hist_defaults.py, module_path: plugins.convert.color, plugin_type: color
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.color.match_hist_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'color.match_hist', info: 'Options for matching the histograms between the source and destination faces')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.match_hist', title: 'threshold', datatype: '<class 'float'>', default: '99.0', info: 'Adjust the threshold for histogram matching. Can reduce extreme colors leaking in by filtering out colors at the extreme ends of the histogram spectrum.', rounding: '1', min_max: (90.0, 100.0), choices: [], gui_radio: False, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: color.match_hist
04/29/2020 12:09:05 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'mask']
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: box_blend_defaults.py, module_path: plugins.convert.mask, plugin_type: mask
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.mask.box_blend_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'mask.box_blend', info: 'Options for blending the edges of the swapped box with the background image')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'type', datatype: '<class 'str'>', default: 'gaussian', info: 'The type of blending to use:\n	 gaussian: Blend with Gaussian filter. Slower, but often better than Normalized\n	 normalized: Blend with Normalized box filter. Faster than Gaussian\n	 none: Don't perform blending', rounding: 'None', min_max: None, choices: ['gaussian', 'normalized', 'none'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'distance', datatype: '<class 'float'>', default: '11.0', info: 'The distance from the edges of the swap box to start blending.\nThe distance is set as percentage of the swap box size to give the number of pixels from the edge of the box. Eg: For a swap area of 256px and a percentage of 4%, blending would commence 10 pixels from the edge.\nHigher percentages start the blending from closer to the center of the face, so will reveal more of the source face.', rounding: '1', min_max: (0.1, 25.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'radius', datatype: '<class 'float'>', default: '5.0', info: 'Radius dictates how much blending should occur, or more specifically, how far the blending will spread away from the 'distance' parameter.\nThis figure is set as a percentage of the swap box size to give the radius in pixels. Eg: For a swap area of 256px and a percentage of 5%, the radius would be 13 pixels\nNB: Higher percentage means more blending, but too high may reveal more of the source face, or lead to hard lines at the border.', rounding: '1', min_max: (0.1, 25.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'passes', datatype: '<class 'int'>', default: '1', info: 'The number of passes to perform. Additional passes of the blending algorithm can improve smoothing at a time cost. This is more useful for 'box' type blending.\nAdditional passes have exponentially less effect so it's not worth setting this too high.', rounding: '1', min_max: (1, 8), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: mask.box_blend
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: mask_blend_defaults.py, module_path: plugins.convert.mask, plugin_type: mask
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.mask.mask_blend_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'mask.mask_blend', info: 'Options for blending the edges between the mask and the background image')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'type', datatype: '<class 'str'>', default: 'normalized', info: 'The type of blending to use:\n	 gaussian: Blend with Gaussian filter. Slower, but often better than Normalized\n	 normalized: Blend with Normalized box filter. Faster than Gaussian\n	 none: Don't perform blending', rounding: 'None', min_max: None, choices: ['gaussian', 'normalized', 'none'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'kernel_size', datatype: '<class 'int'>', default: '3', info: 'The kernel size dictates how much blending should occur.\nThe size is the diameter of the kernel in pixels (calculated from a 128px mask).  This value should be odd, if an even number is passed in then it will be rounded to the next odd number. Higher sizes means more blending.', rounding: '1', min_max: (1, 9), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'passes', datatype: '<class 'int'>', default: '4', info: 'The number of passes to perform. Additional passes of the blending algorithm can improve smoothing at a time cost. This is more useful for 'box' type blending.\nAdditional passes have exponentially less effect so it's not worth setting this too high.', rounding: '1', min_max: (1, 8), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'threshold', datatype: '<class 'int'>', default: '4', info: 'Sets pixels that are near white to white and near black to black. Set to 0 for off.', rounding: '1', min_max: (0, 50), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'erosion', datatype: '<class 'float'>', default: '0.0', info: 'Erosion kernel size as a percentage of the mask radius area.\nPositive values apply erosion which reduces the size of the swapped area.\nNegative values apply dilation which increases the swapped area.', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: mask.mask_blend
04/29/2020 12:09:05 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'scaling']
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: sharpen_defaults.py, module_path: plugins.convert.scaling, plugin_type: scaling
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.scaling.sharpen_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'scaling.sharpen', info: 'Options for sharpening the face after placement')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'method', datatype: '<class 'str'>', default: 'unsharp_mask', info: 'The type of sharpening to use:\n	 box: Fastest, but weakest method. Uses a box filter to assess edges.\n	 gaussian: Slower, but better than box. Uses a gaussian filter to assess edges.\n	 unsharp-mask: Slowest, but most tweakable. Uses the unsharp-mask method to assess edges.', rounding: 'None', min_max: None, choices: ['box', 'gaussian', 'unsharp_mask'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'amount', datatype: '<class 'int'>', default: '150', info: 'Percentage that controls the magnitude of each overshoot (how much darker and how much lighter the edge borders become).\nThis can also be thought of as how much contrast is added at the edges. It does not affect the width of the edge rims.', rounding: '1', min_max: (100, 500), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'radius', datatype: '<class 'float'>', default: '0.3', info: 'Affects the size of the edges to be enhanced or how wide the edge rims become, so a smaller radius enhances smaller-scale detail.\nRadius is set as a percentage of the final frame width and rounded to the nearest pixel. E.g for a 1280 width frame, a 0.6 percenatage will give a radius of 8px.\nHigher radius values can cause halos at the edges, a detectable faint light rim around objects. Fine detail needs a smaller radius. \nRadius and amount interact; reducing one allows more of the other.', rounding: '1', min_max: (0.1, 5.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'threshold', datatype: '<class 'float'>', default: '5.0', info: '[unsharp_mask only] Controls the minimal brightness change that will be sharpened or how far apart adjacent tonal values have to be before the filter does anything.\nThis lack of action is important to prevent smooth areas from becoming speckled. The threshold setting can be used to sharpen more pronounced edges, while leaving subtler edges untouched. \nLow values should sharpen more because fewer areas are excluded. \nHigher threshold values exclude areas of lower contrast.', rounding: '1', min_max: (1.0, 10.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: scaling.sharpen
04/29/2020 12:09:05 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'writer']
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: ffmpeg_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.ffmpeg_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.ffmpeg', info: 'Options for encoding converted frames to video.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'container', datatype: '<class 'str'>', default: 'mp4', info: 'Video container to use.', rounding: 'None', min_max: None, choices: ['avi', 'flv', 'mkv', 'mov', 'mp4', 'mpeg', 'webm'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'codec', datatype: '<class 'str'>', default: 'libx264', info: 'Video codec to use:\n	 libx264: H.264. A widely supported and commonly used codec.\n	 libx265: H.265 / HEVC video encoder application library.', rounding: 'None', min_max: None, choices: ['libx264', 'libx265'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'crf', datatype: '<class 'int'>', default: '23', info: 'Constant Rate Factor:  0 is lossless and 51 is worst quality possible. A lower value generally leads to higher quality, and a subjectively sane range is 17-28. Consider 17 or 18 to be visually lossless or nearly so; it should look the same or nearly the same as the input but it isn't technically lossless.\nThe range is exponential, so increasing the CRF value +6 results in roughly half the bitrate / file size, while -6 leads to roughly twice the bitrate.', rounding: '1', min_max: (0, 51), choices: [], gui_radio: False, fixed: True, group: quality)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'preset', datatype: '<class 'str'>', default: 'medium', info: 'A preset is a collection of options that will provide a certain encoding speed to compression ratio.\nA slower preset will provide better compression (compression is quality per filesize).\nUse the slowest preset that you have patience for.', rounding: 'None', min_max: None, choices: ['ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow'], gui_radio: True, fixed: True, group: quality)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'tune', datatype: '<class 'str'>', default: 'none', info: 'Change settings based upon the specifics of your input:\n	 none: Don't perform any additional tuning.\n	 film: [H.264 only] Use for high quality movie content; lowers deblocking.\n	 animation: [H.264 only] Good for cartoons; uses higher deblocking and more reference frames.\n	 grain: Preserves the grain structure in old, grainy film material.\n	 stillimage: [H.264 only] Good for slideshow-like content.\n	 fastdecode: Allows faster decoding by disabling certain filters.\n	 zerolatency: Good for fast encoding and low-latency streaming.', rounding: 'None', min_max: None, choices: ['none', 'film', 'animation', 'grain', 'stillimage', 'fastdecode', 'zerolatency'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'profile', datatype: '<class 'str'>', default: 'auto', info: '[H.264 Only] Limit the output to a specific H.264 profile. Don't change this unless your target device only supports a certain profile.', rounding: 'None', min_max: None, choices: ['auto', 'baseline', 'main', 'high', 'high10', 'high422', 'high444'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'level', datatype: '<class 'str'>', default: 'auto', info: '[H.264 Only] Set the encoder level, Don't change this unless your target device only supports a certain level.', rounding: 'None', min_max: None, choices: ['auto', '1', '1b', '1.1', '1.2', '1.3', '2', '2.1', '2.2', '3', '3.1', '3.2', '4', '4.1', '4.2', '5', '5.1', '5.2', '6', '6.1', '6.2'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.ffmpeg
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: gif_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.gif_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.gif', info: 'Options for outputting converted frames to an animated gif.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'fps', datatype: '<class 'int'>', default: '25', info: 'Frames per Second.', rounding: '1', min_max: (1, 60), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'loop', datatype: '<class 'int'>', default: '0', info: 'The number of iterations. Set to 0 to loop indefinitely.', rounding: '1', min_max: (0, 100), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'palettesize', datatype: '<class 'str'>', default: '256', info: 'The number of colors to quantize the image to. Is rounded to the nearest power of two.', rounding: 'None', min_max: None, choices: ['2', '4', '8', '16', '32', '64', '128', '256'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'subrectangles', datatype: '<class 'bool'>', default: 'False', info: 'If True, will try and optimize the GIF by storing only the rectangular parts of each frame that change with respect to the previous.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.gif
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: opencv_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.opencv_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.opencv', info: 'Options for outputting converted frames to a series of images using OpenCV\nOpenCV can be faster than other image writers, but lacks some configuration options and formats.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'format', datatype: '<class 'str'>', default: 'png', info: 'Image format to use:\n	 bmp: Windows bitmap\n	 jpg: JPEG format\n	 jp2: JPEG 2000 format\n	 png: Portable Network Graphics\n	 ppm: Portable Pixmap Format', rounding: 'None', min_max: None, choices: ['bmp', 'jpg', 'jp2', 'png', 'ppm'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'draw_transparent', datatype: '<class 'bool'>', default: 'False', info: 'Place the swapped face on a transparent layer rather than the original frame.\nNB: This is only compatible with images saved in png format. If an incompatible format is selected then the image will be saved as a png.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'jpg_quality', datatype: '<class 'int'>', default: '75', info: '[jpg only] Set the jpg quality. 1 is worst 95 is best. Higher quality leads to larger file sizes.', rounding: '1', min_max: (1, 95), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'png_compress_level', datatype: '<class 'int'>', default: '3', info: '[png only] ZLIB compression level, 1 gives best speed, 9 gives best compression, 0 gives no compression at all.', rounding: '1', min_max: (0, 9), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.opencv
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: pillow_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.pillow_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.pillow', info: 'Options for outputting converted frames to a series of images using Pillow\nPillow is more feature rich than OpenCV but can be slower.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'format', datatype: '<class 'str'>', default: 'png', info: 'Image format to use:\n	 bmp: Windows bitmap\n	 gif: Graphics Interchange Format (NB: Not animated)\n	 jpg: JPEG format\n	 jp2: JPEG 2000 format\n	 png: Portable Network Graphics\n	 ppm: Portable Pixmap Format\n	 tif: Tag Image File Format', rounding: 'None', min_max: None, choices: ['bmp', 'gif', 'jpg', 'jp2', 'png', 'ppm', 'tif'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'draw_transparent', datatype: '<class 'bool'>', default: 'False', info: 'Place the swapped face on a transparent layer rather than the original frame.\nNB: This is only compatible with images saved in png or tif format. If an incompatible format is selected then the image will be saved as a png.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'optimize', datatype: '<class 'bool'>', default: 'False', info: '[gif, jpg and png only] If enabled, indicates that the encoder should make an extra pass over the image in order to select optimal encoder settings.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'gif_interlace', datatype: '<class 'bool'>', default: 'True', info: '[gif only] Set whether to save the gif as interlaced or not.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'jpg_quality', datatype: '<class 'int'>', default: '75', info: '[jpg only] Set the jpg quality. 1 is worst 95 is best. Higher quality leads to larger file sizes.', rounding: '1', min_max: (1, 95), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'png_compress_level', datatype: '<class 'int'>', default: '3', info: '[png only] ZLIB compression level, 1 gives best speed, 9 gives best compression, 0 gives no compression at all. When optimize option is set to True this has no effect (it is set to 9 regardless of a value passed).', rounding: '1', min_max: (0, 9), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'tif_compression', datatype: '<class 'str'>', default: 'tiff_deflate', info: '[tif only] The desired compression method for the file.', rounding: 'None', min_max: None, choices: ['none', 'tiff_ccitt', 'group3', 'group4', 'tiff_jpeg', 'tiff_adobe_deflate', 'tiff_thunderscan', 'tiff_deflate', 'tiff_sgilog', 'tiff_sgilog24', 'tiff_raw_16'], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.pillow
04/29/2020 12:09:05 MainProcess     MainThread      config          handle_config             DEBUG    Handling config
04/29/2020 12:09:05 MainProcess     MainThread      config          check_exists              DEBUG    Config file exists: 'D:\Testing\faceswap\config\convert.ini'
04/29/2020 12:09:05 MainProcess     MainThread      config          load_config               VERBOSE  Loading config: 'D:\Testing\faceswap\config\convert.ini'
04/29/2020 12:09:05 MainProcess     MainThread      config          validate_config           DEBUG    Validating config
04/29/2020 12:09:05 MainProcess     MainThread      config          check_config_change       DEBUG    Default config has not changed
04/29/2020 12:09:05 MainProcess     MainThread      config          check_config_choices      DEBUG    Checking config choices
04/29/2020 12:09:05 MainProcess     MainThread      config          check_config_choices      DEBUG    Checked config choices
04/29/2020 12:09:05 MainProcess     MainThread      config          validate_config           DEBUG    Validated config
04/29/2020 12:09:05 MainProcess     MainThread      config          handle_config             DEBUG    Handled config
04/29/2020 12:09:05 MainProcess     MainThread      config          __init__                  DEBUG    Initialized: Config
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'writer.opencv', option: 'format')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'str'>, value: png)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'writer.opencv', option: 'draw_transparent')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'bool'>, value: False)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'writer.opencv', option: 'jpg_quality')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'int'>, value: 75)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'writer.opencv', option: 'png_compress_level')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'int'>, value: 3)
04/29/2020 12:09:05 MainProcess     MainThread      _base           __init__                  DEBUG    config: {'format': 'png', 'draw_transparent': False, 'jpg_quality': 75, 'png_compress_level': 3}
04/29/2020 12:09:05 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized Writer
04/29/2020 12:09:05 MainProcess     MainThread      opencv          get_save_args             DEBUG    (16, 3)
04/29/2020 12:09:05 MainProcess     MainThread      alignments      have_alignments_file      TRACE    True
04/29/2020 12:09:05 MainProcess     MainThread      alignments      have_alignments_file      TRACE    True
04/29/2020 12:09:05 MainProcess     MainThread      convert         _load_extractor           DEBUG    Alignments file found: 'D:\Testing\faceswap\Extract\Source\source_test1\source_test1\alignments.fsa'
04/29/2020 12:09:05 MainProcess     MainThread      convert         _init_threads             DEBUG    Initializing DiskIO Threads
04/29/2020 12:09:05 MainProcess     MainThread      convert         _add_queue                DEBUG    Adding queue for task: 'load'
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager getting: 'convert_in'
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager got: 'convert_in'
04/29/2020 12:09:05 MainProcess     MainThread      convert         _add_queue                DEBUG    Added queue for task: 'load'
04/29/2020 12:09:05 MainProcess     MainThread      convert         _start_thread             DEBUG    Starting thread: 'load'
04/29/2020 12:09:05 MainProcess     MainThread      multithreading  __init__                  DEBUG    Initializing MultiThread: (target: '_load', thread_count: 1)
04/29/2020 12:09:05 MainProcess     MainThread      multithreading  __init__                  TRACE    args: (None,), kwargs: {}
04/29/2020 12:09:05 MainProcess     MainThread      multithreading  __init__                  DEBUG    Initialized MultiThread: '_load'
04/29/2020 12:09:05 MainProcess     MainThread      multithreading  start                     DEBUG    Starting thread(s): '_load'
04/29/2020 12:09:05 MainProcess     MainThread      multithreading  start                     DEBUG    Starting thread 1 of 1: '_load_0'
04/29/2020 12:09:05 MainProcess     _load_0         convert         _load                     DEBUG    Load Images: Start
04/29/2020 12:09:05 MainProcess     MainThread      multithreading  start                     DEBUG    Started all threads '_load': 1
04/29/2020 12:09:05 MainProcess     _load_0         image           load                      DEBUG    Initializing Load Generator
04/29/2020 12:09:05 MainProcess     MainThread      convert         _start_thread             DEBUG    Started thread: 'load'
04/29/2020 12:09:05 MainProcess     _load_0         image           _set_thread               DEBUG    Setting thread
04/29/2020 12:09:05 MainProcess     MainThread      convert         _add_queue                DEBUG    Adding queue for task: 'save'
04/29/2020 12:09:05 MainProcess     _load_0         multithreading  __init__                  DEBUG    Initializing MultiThread: (target: 'ImagesLoader', thread_count: 1)
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager getting: 'convert_out'
04/29/2020 12:09:05 MainProcess     _load_0         multithreading  __init__                  TRACE    args: (<queue.Queue object at 0x00000260F3F59A48>,), kwargs: {}
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager got: 'convert_out'
04/29/2020 12:09:05 MainProcess     _load_0         multithreading  __init__                  DEBUG    Initialized MultiThread: 'ImagesLoader'
04/29/2020 12:09:05 MainProcess     MainThread      convert         _add_queue                DEBUG    Added queue for task: 'save'
04/29/2020 12:09:05 MainProcess     _load_0         image           _set_thread               DEBUG    Set thread: <lib.multithreading.MultiThread object at 0x00000260F5757848>
04/29/2020 12:09:05 MainProcess     MainThread      convert         _start_thread             DEBUG    Starting thread: 'save'
04/29/2020 12:09:05 MainProcess     _load_0         multithreading  start                     DEBUG    Starting thread(s): 'ImagesLoader'
04/29/2020 12:09:05 MainProcess     MainThread      multithreading  __init__                  DEBUG    Initializing MultiThread: (target: '_save', thread_count: 1)
04/29/2020 12:09:05 MainProcess     _load_0         multithreading  start                     DEBUG    Starting thread 1 of 1: 'ImagesLoader_0'
04/29/2020 12:09:05 MainProcess     MainThread      multithreading  __init__                  TRACE    args: (<threading.Event object at 0x00000260F5983948>,), kwargs: {}
04/29/2020 12:09:05 MainProcess     MainThread      multithreading  __init__                  DEBUG    Initialized MultiThread: '_save'
04/29/2020 12:09:05 MainProcess     MainThread      multithreading  start                     DEBUG    Starting thread(s): '_save'
04/29/2020 12:09:05 MainProcess     ImagesLoader_0  image           _process                  DEBUG    Load iterator: <bound method ImagesLoader._from_folder of <lib.image.ImagesLoader object at 0x00000260F4446448>>
04/29/2020 12:09:05 MainProcess     MainThread      multithreading  start                     DEBUG    Starting thread 1 of 1: '_save_0'
04/29/2020 12:09:05 MainProcess     _load_0         multithreading  start                     DEBUG    Started all threads 'ImagesLoader': 1
04/29/2020 12:09:05 MainProcess     ImagesLoader_0  image           _from_folder              DEBUG    Loading frames from folder: 'D:\Testing\faceswap\Extract\Source\source_test1'
04/29/2020 12:09:05 MainProcess     _save_0         convert         _save                     DEBUG    Save Images: Start
04/29/2020 12:09:05 MainProcess     ImagesLoader_0  image           _process                  TRACE    Putting EOF
04/29/2020 12:09:05 MainProcess     MainThread      multithreading  start                     DEBUG    Started all threads '_save': 1
04/29/2020 12:09:05 MainProcess     _save_0         convert         _save                     DEBUG    Write preview for gui: False
04/29/2020 12:09:05 MainProcess     _load_0         image           load                      TRACE    Got EOF
04/29/2020 12:09:05 MainProcess     MainThread      convert         _start_thread             DEBUG    Started thread: 'save'
04/29/2020 12:09:05 MainProcess     _save_0         convert         _total_count              DEBUG    0
04/29/2020 12:09:05 MainProcess     _load_0         image           load                      DEBUG    Closing Load Generator
04/29/2020 12:09:05 MainProcess     MainThread      convert         _init_threads             DEBUG    Initialized DiskIO Threads
04/29/2020 12:09:05 MainProcess     _load_0         image           close                     DEBUG    Received Close
04/29/2020 12:09:05 MainProcess     MainThread      convert         __init__                  DEBUG    Initialized DiskIO
04/29/2020 12:09:05 MainProcess     _load_0         multithreading  join                      DEBUG    Joining Threads: 'ImagesLoader'
04/29/2020 12:09:05 MainProcess     MainThread      convert         _queue_size               DEBUG    32
04/29/2020 12:09:05 MainProcess     _load_0         multithreading  join                      DEBUG    Joining Thread: 'ImagesLoader_0'
04/29/2020 12:09:05 MainProcess     MainThread      convert         __init__                  DEBUG    Initializing Predict: (args: Namespace(alignments_path='D:\\Testing\\faceswap\\Extract\\Source\\source_test1\\source_test1\\alignments.fsa', allow_growth=False, colab=False, color_adjustment='avg-color', configfile=None, filter=None, frame_ranges=None, func=<bound method ScriptExecutor.execute_script of <lib.cli.launcher.ScriptExecutor object at 0x00000260EB9D09C8>>, gpus=1, input_aligned_dir=None, input_dir='D:\\Testing\\faceswap\\Extract\\Source\\source_test1', jobs=0, keep_unchanged=False, logfile='D:\\Testing\\faceswap\\Extract\\log_test1.log', loglevel='TRACE', mask_type='none', model_dir='D:\\Testing\\faceswap\\Extract\\Model\\model_test1', nfilter=None, on_the_fly=False, output_dir='D:\\Testing\\faceswap\\Extract\\Convert\\test2', output_scale=100, redirect_gui=True, ref_threshold=0.4, reference_video=None, scaling='none', singleprocess=False, swap_model=False, trainer=None, writer='opencv'), queue_size: 32, in_queue: <queue.Queue object at 0x00000260F474B548>)
04/29/2020 12:09:05 MainProcess     _load_0         multithreading  join                      DEBUG    Joined all Threads: 'ImagesLoader'
04/29/2020 12:09:05 MainProcess     MainThread      convert         _get_batchsize            DEBUG    Getting batchsize
04/29/2020 12:09:05 MainProcess     _load_0         image           close                     DEBUG    Closed
04/29/2020 12:09:05 MainProcess     MainThread      gpu_stats       _log                      DEBUG    Initializing GPUStats
04/29/2020 12:09:05 MainProcess     _load_0         convert         _load                     DEBUG    Putting EOF
04/29/2020 12:09:05 MainProcess     MainThread      gpu_stats       _log                      DEBUG    OS is not macOS. Trying pynvml
04/29/2020 12:09:05 MainProcess     _load_0         convert         _load                     DEBUG    Load Images: Complete
04/29/2020 12:09:05 MainProcess     _save_0         convert         _save                     DEBUG    Save Faces: Complete
04/29/2020 12:09:05 MainProcess     MainThread      gpu_stats       _log                      DEBUG    GPU Device count: 1
04/29/2020 12:09:05 MainProcess     MainThread      gpu_stats       _log                      DEBUG    Active GPU Devices: [0]
04/29/2020 12:09:05 MainProcess     MainThread      gpu_stats       _log                      DEBUG    GPU Handles found: 1
04/29/2020 12:09:05 MainProcess     MainThread      gpu_stats       _log                      DEBUG    GPU Driver: 442.74
04/29/2020 12:09:05 MainProcess     MainThread      gpu_stats       _log                      DEBUG    GPU Devices: ['GeForce GTX 1070 Ti']
04/29/2020 12:09:05 MainProcess     MainThread      gpu_stats       _log                      DEBUG    GPU VRAM: [8192.0]
04/29/2020 12:09:05 MainProcess     MainThread      gpu_stats       _log                      DEBUG    Initialized GPUStats
04/29/2020 12:09:05 MainProcess     MainThread      convert         _get_batchsize            DEBUG    Batchsize: 16
04/29/2020 12:09:05 MainProcess     MainThread      convert         _get_batchsize            DEBUG    Got batchsize: 16
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager getting: 'patch'
04/29/2020 12:09:05 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager got: 'patch'
04/29/2020 12:09:05 MainProcess     MainThread      serializer      get_serializer            DEBUG    <lib.serializer._JSONSerializer object at 0x00000260F5744C48>
04/29/2020 12:09:05 MainProcess     MainThread      convert         _load_model               DEBUG    Loading Model
04/29/2020 12:09:05 MainProcess     MainThread      utils           get_folder                DEBUG    Requested path: 'D:\Testing\faceswap\Extract\Model\model_test1'
04/29/2020 12:09:05 MainProcess     MainThread      utils           get_folder                DEBUG    Returning: 'D:\Testing\faceswap\Extract\Model\model_test1'
04/29/2020 12:09:05 MainProcess     MainThread      serializer      load                      DEBUG    filename: D:\Testing\faceswap\Extract\Model\model_test1\original_state.json
04/29/2020 12:09:05 MainProcess     MainThread      serializer      load                      DEBUG    stored data type: <class 'bytes'>
04/29/2020 12:09:05 MainProcess     MainThread      serializer      unmarshal                 DEBUG    data type: <class 'bytes'>
04/29/2020 12:09:05 MainProcess     MainThread      serializer      unmarshal                 DEBUG    returned data type: <class 'dict'>
04/29/2020 12:09:05 MainProcess     MainThread      serializer      load                      DEBUG    data type: <class 'dict'>
04/29/2020 12:09:05 MainProcess     MainThread      convert         _get_model_name           DEBUG    Trainer from state file: 'original'
04/29/2020 12:09:05 MainProcess     MainThread      plugin_loader   _import                   INFO     Loading Model from Original plugin...
04/29/2020 12:09:05 MainProcess     MainThread      original        __init__                  DEBUG    Initializing Model: (args: (WindowsPath('D:/Testing/faceswap/Extract/Model/model_test1'), 1), kwargs: {'predict': True}
04/29/2020 12:09:05 MainProcess     MainThread      _base           config_section            DEBUG    model.original
04/29/2020 12:09:05 MainProcess     MainThread      _base           config                    DEBUG    Loading config for: model.original
04/29/2020 12:09:05 MainProcess     MainThread      config          __init__                  DEBUG    Initializing: Config
04/29/2020 12:09:05 MainProcess     MainThread      config          get_config_file           DEBUG    Config File location: 'D:\Testing\faceswap\config\train.ini'
04/29/2020 12:09:05 MainProcess     MainThread      _config         set_defaults              DEBUG    Setting defaults
04/29/2020 12:09:05 MainProcess     MainThread      _config         set_globals               DEBUG    Setting global config
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'global', info: 'Options that apply to all models\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'coverage', datatype: '<class 'float'>', default: '68.75', info: 'How much of the extracted image to train on. A lower coverage will limit the model's scope to a zoomed-in central area while higher amounts can include the entire face. A trade-off exists between lower amounts given more detail versus higher amounts avoiding noticeable swap transitions. Sensible values to use are:\n	62.5%% spans from eyebrow to eyebrow.\n	75.0%% spans from temple to temple.\n	87.5%% spans from ear to ear.\n	100.0%% is a mugshot.', rounding: '2', min_max: (62.5, 100.0), choices: None, gui_radio: False, fixed: True, group: face)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'mask_type', datatype: '<class 'str'>', default: 'none', info: 'The mask to be used for training. If you have selected 'Learn Mask' or 'Penalized Mask Loss' you must select a value other than 'none'. The required mask should have been selected as part of the Extract process. If it does not exist in the alignments file then it will be generated prior to training commencing.\n	none: Don't use a mask.\n	components: Mask designed to provide facial segmentation based on the positioning of landmark locations. A convex hull is constructed around the exterior of the landmarks to create a mask.\n	extended: Mask designed to provide facial segmentation based on the positioning of landmark locations. A convex hull is constructed around the exterior of the landmarks and the mask is extended upwards onto the forehead.\n	vgg-clear: Mask designed to provide smart segmentation of mostly frontal faces clear of obstructions. Profile faces and obstructions may result in sub-par performance.\n	vgg-obstructed: Mask designed to provide smart segmentation of mostly frontal faces. The mask model has been specifically trained to recognize some facial obstructions (hands and eyeglasses). Profile faces may result in sub-par performance.\n	unet-dfl: Mask designed to provide smart segmentation of mostly frontal faces. The mask model has been trained by community members and will need testing for further description. Profile faces may result in sub-par performance.', rounding: 'None', min_max: None, choices: ['none', 'components', 'extended', 'unet-dfl', 'vgg-clear', 'vgg-obstructed'], gui_radio: True, fixed: True, group: mask)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'mask_blur_kernel', datatype: '<class 'int'>', default: '3', info: 'Apply gaussian blur to the mask input. This has the effect of smoothing the edges of the mask, which can help with poorly calculated masks and give less of a hard edge to the predicted mask. The size is in pixels (calculated from a 128px mask). Set to 0 to not apply gaussian blur. This value should be odd, if an even number is passed in then it will be rounded to the next odd number.', rounding: '1', min_max: (0, 9), choices: None, gui_radio: False, fixed: True, group: mask)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'mask_threshold', datatype: '<class 'int'>', default: '4', info: 'Sets pixels that are near white to white and near black to black. Set to 0 for off.', rounding: '1', min_max: (0, 50), choices: None, gui_radio: False, fixed: True, group: mask)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'learn_mask', datatype: '<class 'bool'>', default: 'False', info: 'Dedicate a portion of the model to learning how to duplicate the input mask. Increases VRAM usage in exchange for learning a quick ability to try to replicate more complex mask models.', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: mask)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'icnr_init', datatype: '<class 'bool'>', default: 'False', info: 'Use ICNR to tile the default initializer in a repeating pattern. This strategy is designed for pairing with sub-pixel / pixel shuffler to reduce the 'checkerboard effect' in image reconstruction. \n	 https://arxiv.org/ftp/arxiv/papers/1707/1707.02937.pdf', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: initialization)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'conv_aware_init', datatype: '<class 'bool'>', default: 'False', info: 'Use Convolution Aware Initialization for convolutional layers. This can help eradicate the vanishing and exploding gradient problem as well as lead to higher accuracy, lower loss and faster convergence.\nNB:\n	 This can use more VRAM when creating a new model so you may want to lower the batch size for the first run. The batch size can be raised again when reloading the model. \n	 Multi-GPU is not supported for this option, so you should start the model on a single GPU. Once training has started, you can stop training, enable multi-GPU and resume.\n	 Building the model will likely take several minutes as the calculations for this initialization technique are expensive. This will only impact starting a new model.', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: initialization)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'subpixel_upscaling', datatype: '<class 'bool'>', default: 'False', info: 'Use subpixel upscaling rather than pixel shuffler. These techniques are both designed to produce better resolving upscaling than other methods. Each perform the same operations, but using different TF opts.\n	 https://arxiv.org/pdf/1609.05158.pdf', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'reflect_padding', datatype: '<class 'bool'>', default: 'False', info: 'Use reflection padding rather than zero padding with convolutions. Each convolution must pad the image boundaries to maintain the proper sizing. More complex padding schemes can reduce artifacts at the border of the image.\n	 http://www-cs.engr.ccny.cuny.edu/~wolberg/cs470/hw/hw2_pad.txt', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'penalized_mask_loss', datatype: '<class 'bool'>', default: 'True', info: 'Image loss function is weighted by mask presence. For areas of the image without the facial mask, reconstuction errors will be ignored while the masked face area is prioritized. May increase overall quality by focusing attention on the core face area.', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: loss)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'loss_function', datatype: '<class 'str'>', default: 'mae', info: '\n	 MAE - Mean absolute error will guide reconstructions of each pixel towards its median value in the training dataset. Robust to outliers but as a median, it can potentially ignore some infrequent image types in the dataset.\n	 MSE - Mean squared error will guide reconstructions of each pixel towards its average value in the training dataset. As an avg, it will be suspectible to outliers and typically produces slightly blurrier results.\n	 LogCosh - log(cosh(x)) acts similiar to MSE for small errors and to MAE for large errors. Like MSE, it is very stable and prevents overshoots when errors are near zero. Like MAE, it is robust to outliers.\n	 Smooth_L1 --- Modification of the MAE loss to correct two of its disadvantages. This loss has improved stability and guidance for small errors.\n	 L_inf_norm --- The L_inf norm will reduce the largest individual pixel error in an image. As each largest error is minimized sequentially, the overall error is improved. This loss will be extremely focused on outliers.\n	 SSIM - Structural Similarity Index Metric is a perception-based loss that considers changes in texture, luminance, contrast, and local spatial statistics of an image. Potentially delivers more realistic looking images.\n	 GMSD - Gradient Magnitude Similarity Deviation seeks to match the global standard deviation of the pixel to pixel differences between two images. Similiar in approach to SSIM.\n	 Pixel_Gradient_Difference - Instead of minimizing the difference between the absolute value of each pixel in two reference images, compute the pixel to pixel spatial difference in each image and then minimize that difference between two images. Allows for large color shifts,but maintains the structure of the image.\n', rounding: 'None', min_max: None, choices: ['mae', 'mse', 'logcosh', 'smooth_loss', 'l_inf_norm', 'ssim', 'gmsd', 'pixel_gradient_diff'], gui_radio: False, fixed: True, group: loss)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'learning_rate', datatype: '<class 'float'>', default: '5e-05', info: 'Learning rate - how fast your network will learn (how large are the modifications to the model weights after one batch of training). Values that are too large might result in model crashes and the inability of the model to find the best solution. Values that are too small might be unable to escape from dead-ends and find the best global minimum.', rounding: '6', min_max: (1e-06, 0.0001), choices: None, gui_radio: False, fixed: False, group: optimizer)
04/29/2020 12:09:05 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'train', 'model']
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: dfl_h128_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.dfl_h128_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.dfl_h128', info: 'DFL H128 Model (Adapted from https://github.com/iperov/DeepFaceLab)\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_h128', title: 'lowmem', datatype: '<class 'bool'>', default: 'False', info: 'Lower memory mode. Set to 'True' if having issues with VRAM useage.\nNB: Models with a changed lowmem mode are not compatible with each other.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.dfl_h128
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: dfl_sae_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.dfl_sae_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.dfl_sae', info: 'DFL SAE Model (Adapted from https://github.com/iperov/DeepFaceLab)\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'input_size', datatype: '<class 'int'>', default: '128', info: 'Resolution (in pixels) of the input image to train on.\nBE AWARE Larger resolution will dramatically increase VRAM requirements.\n\nMust be divisible by 16.', rounding: '16', min_max: (64, 256), choices: None, gui_radio: False, fixed: True, group: size)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'clipnorm', datatype: '<class 'bool'>', default: 'True', info: 'Controls gradient clipping of the optimizer. Can prevent model corruption at the expense of VRAM.', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: False, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'architecture', datatype: '<class 'str'>', default: 'df', info: 'Model architecture:\n	'df': Keeps the faces more natural.\n	'liae': Can help fix overly different face shapes.', rounding: 'None', min_max: None, choices: ['df', 'liae'], gui_radio: True, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'autoencoder_dims', datatype: '<class 'int'>', default: '0', info: 'Face information is stored in AutoEncoder dimensions. If there are not enough dimensions then certain facial features may not be recognized.\nHigher number of dimensions are better, but require more VRAM.\nSet to 0 to use the architecture defaults (256 for liae, 512 for df).', rounding: '32', min_max: (0, 1024), choices: None, gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'encoder_dims', datatype: '<class 'int'>', default: '42', info: 'Encoder dimensions per channel. Higher number of encoder dimensions will help the model to recognize more facial features, but will require more VRAM.', rounding: '1', min_max: (21, 85), choices: None, gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'decoder_dims', datatype: '<class 'int'>', default: '21', info: 'Decoder dimensions per channel. Higher number of decoder dimensions will help the model to improve details, but will require more VRAM.', rounding: '1', min_max: (10, 85), choices: None, gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'multiscale_decoder', datatype: '<class 'bool'>', default: 'False', info: 'Multiscale decoder can help to obtain better details.', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.dfl_sae
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: dlight_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.dlight_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.dlight', info: 'A lightweight, high resolution Dfaker variant (Adapted from https://github.com/dfaker/df)\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dlight', title: 'features', datatype: '<class 'str'>', default: 'best', info: 'Higher settings will allow learning more features such as tatoos, piercing,\nand wrinkles.\nStrongly affects VRAM usage.', rounding: 'None', min_max: None, choices: ['lowmem', 'fair', 'best'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dlight', title: 'details', datatype: '<class 'str'>', default: 'good', info: 'Defines detail fidelity. Lower setting can appear 'rugged' while 'good' might take onger time to train.\nAffects VRAM usage.', rounding: 'None', min_max: None, choices: ['fast', 'good'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dlight', title: 'output_size', datatype: '<class 'int'>', default: '256', info: 'Output image resolution (in pixels).\nBe aware that larger resolution will increase VRAM requirements.\nNB: Must be either 128, 256, or 384.', rounding: '128', min_max: (128, 384), choices: [], gui_radio: False, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.dlight
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: original_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.original_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.original', info: 'Original Faceswap Model.\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.original', title: 'lowmem', datatype: '<class 'bool'>', default: 'False', info: 'Lower memory mode. Set to 'True' if having issues with VRAM useage.\nNB: Models with a changed lowmem mode are not compatible with each other.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.original
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: realface_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.realface_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.realface', info: 'An extra detailed variant of Original model.\nIncorporates ideas from Bryanlyon and inspiration from the Villain model.\nRequires about 6GB-8GB of VRAM (batchsize 8-16).\n\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.realface', title: 'input_size', datatype: '<class 'int'>', default: '64', info: 'Resolution (in pixels) of the input image to train on.\nBE AWARE Larger resolution will dramatically increase VRAM requirements.\nHigher resolutions may increase prediction accuracy, but does not effect the resulting output size.\nMust be between 64 and 128 and be divisible by 16.', rounding: '16', min_max: (64, 128), choices: [], gui_radio: False, fixed: True, group: size)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.realface', title: 'output_size', datatype: '<class 'int'>', default: '128', info: 'Output image resolution (in pixels).\nBe aware that larger resolution will increase VRAM requirements.\nNB: Must be between 64 and 256 and be divisible by 16.', rounding: '16', min_max: (64, 256), choices: [], gui_radio: False, fixed: True, group: size)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.realface', title: 'dense_nodes', datatype: '<class 'int'>', default: '1536', info: 'Number of nodes for decoder. Might affect your model's ability to learn in general.\nNote that: Lower values will affect the ability to predict details.', rounding: '64', min_max: (768, 2048), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.realface', title: 'complexity_encoder', datatype: '<class 'int'>', default: '128', info: 'Encoder Convolution Layer Complexity. sensible ranges: 128 to 150.', rounding: '4', min_max: (96, 160), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.realface', title: 'complexity_decoder', datatype: '<class 'int'>', default: '512', info: 'Decoder Complexity.', rounding: '4', min_max: (512, 544), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.realface
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: unbalanced_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.unbalanced_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.unbalanced', info: 'An unbalanced model with adjustable input size options.\nThis is an unbalanced model so b>a swaps may not work well\n\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'input_size', datatype: '<class 'int'>', default: '128', info: 'Resolution (in pixels) of the image to train on.\nBE AWARE Larger resolution will dramatically increaseVRAM requirements.\nMake sure your resolution is divisible by 64 (e.g. 64, 128, 256 etc.).\nNB: Your faceset must be at least 1.6x larger than your required input size.\n(e.g. 160 is the maximum input size for a 256x256 faceset).', rounding: '64', min_max: (64, 512), choices: [], gui_radio: False, fixed: True, group: size)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'lowmem', datatype: '<class 'bool'>', default: 'False', info: 'Lower memory mode. Set to 'True' if having issues with VRAM useage.\nNB: Models with a changed lowmem mode are not compatible with each other.\nNB: lowmem will override cutom nodes and complexity settings.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'clipnorm', datatype: '<class 'bool'>', default: 'True', info: 'Controls gradient clipping of the optimizer. Can prevent model corruption at the expense of VRAM.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'nodes', datatype: '<class 'int'>', default: '1024', info: 'Number of nodes for decoder. Don't change this unless you know what you are doing!', rounding: '64', min_max: (512, 4096), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'complexity_encoder', datatype: '<class 'int'>', default: '128', info: 'Encoder Convolution Layer Complexity. sensible ranges: 128 to 160.', rounding: '16', min_max: (64, 1024), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'complexity_decoder_a', datatype: '<class 'int'>', default: '384', info: 'Decoder A Complexity.', rounding: '16', min_max: (64, 1024), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'complexity_decoder_b', datatype: '<class 'int'>', default: '512', info: 'Decoder B Complexity.', rounding: '16', min_max: (64, 1024), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.unbalanced
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: villain_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.villain_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.villain', info: 'A Higher resolution version of the Original Model by VillainGuy.\nExtremely VRAM heavy. Full model requires 9GB+ for batchsize 16\n\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.villain', title: 'lowmem', datatype: '<class 'bool'>', default: 'False', info: 'Lower memory mode. Set to 'True' if having issues with VRAM useage.\nNB: Models with a changed lowmem mode are not compatible with each other.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.villain
04/29/2020 12:09:05 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'train', 'trainer']
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: original_defaults.py, module_path: plugins.train.trainer, plugin_type: trainer
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.trainer.original_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'trainer.original', info: 'Original Trainer Options.\nWARNING: The defaults for augmentation will be fine for 99.9% of use cases. Only change them if you absolutely know what you are doing!')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'preview_images', datatype: '<class 'int'>', default: '14', info: 'Number of sample faces to display for each side in the preview when training.', rounding: '2', min_max: (2, 16), choices: None, gui_radio: False, fixed: True, group: evaluation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'zoom_amount', datatype: '<class 'int'>', default: '5', info: 'Percentage amount to randomly zoom each training image in and out.', rounding: '1', min_max: (0, 25), choices: None, gui_radio: False, fixed: True, group: image augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'rotation_range', datatype: '<class 'int'>', default: '10', info: 'Percentage amount to randomly rotate each training image.', rounding: '1', min_max: (0, 25), choices: None, gui_radio: False, fixed: True, group: image augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'shift_range', datatype: '<class 'int'>', default: '5', info: 'Percentage amount to randomly shift each training image horizontally and vertically.', rounding: '1', min_max: (0, 25), choices: None, gui_radio: False, fixed: True, group: image augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'flip_chance', datatype: '<class 'int'>', default: '50', info: 'Percentage chance to randomly flip each training image horizontally.\nNB: This is ignored if the 'no-flip' option is enabled', rounding: '1', min_max: (0, 75), choices: None, gui_radio: False, fixed: True, group: image augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'color_lightness', datatype: '<class 'int'>', default: '30', info: 'Percentage amount to randomly alter the lightness of each training image.\nNB: This is ignored if the 'no-augment-color' option is enabled', rounding: '1', min_max: (0, 75), choices: None, gui_radio: False, fixed: True, group: color augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'color_ab', datatype: '<class 'int'>', default: '8', info: 'Percentage amount to randomly alter the 'a' and 'b' colors of the L*a*b* color space of each training image.\nNB: This is ignored if the 'no-augment-color' option is enabled', rounding: '1', min_max: (0, 50), choices: None, gui_radio: False, fixed: True, group: color augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'color_clahe_chance', datatype: '<class 'int'>', default: '50', info: 'Percentage chance to perform Contrast Limited Adaptive Histogram Equalization on each training image.\nNB: This is ignored if the 'no-augment-color' option is enabled', rounding: '1', min_max: (0, 75), choices: None, gui_radio: False, fixed: False, group: color augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'color_clahe_max_size', datatype: '<class 'int'>', default: '4', info: 'The grid size dictates how much Contrast Limited Adaptive Histogram Equalization is performed on any training image selected for clahe. Contrast will be applied randomly with a gridsize of 0 up to the maximum. This value is a multiplier calculated from the training image size.\nNB: This is ignored if the 'no-augment-color' option is enabled', rounding: '1', min_max: (1, 8), choices: None, gui_radio: False, fixed: True, group: color augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: trainer.original
04/29/2020 12:09:05 MainProcess     MainThread      config          handle_config             DEBUG    Handling config
04/29/2020 12:09:05 MainProcess     MainThread      config          check_exists              DEBUG    Config file exists: 'D:\Testing\faceswap\config\train.ini'
04/29/2020 12:09:05 MainProcess     MainThread      config          load_config               VERBOSE  Loading config: 'D:\Testing\faceswap\config\train.ini'
04/29/2020 12:09:05 MainProcess     MainThread      config          validate_config           DEBUG    Validating config
04/29/2020 12:09:05 MainProcess     MainThread      config          check_config_change       DEBUG    Default config has not changed
04/29/2020 12:09:05 MainProcess     MainThread      config          check_config_choices      DEBUG    Checking config choices
04/29/2020 12:09:05 MainProcess     MainThread      config          check_config_choices      DEBUG    Checked config choices
04/29/2020 12:09:05 MainProcess     MainThread      config          validate_config           DEBUG    Validated config
04/29/2020 12:09:05 MainProcess     MainThread      config          handle_config             DEBUG    Handled config
04/29/2020 12:09:05 MainProcess     MainThread      config          __init__                  DEBUG    Initialized: Config
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'coverage')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'float'>, value: 68.75)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'mask_type')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'str'>, value: None)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'mask_blur_kernel')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'int'>, value: 3)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'mask_threshold')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'int'>, value: 4)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'learn_mask')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'bool'>, value: False)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'icnr_init')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'bool'>, value: False)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'conv_aware_init')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'bool'>, value: False)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'subpixel_upscaling')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'bool'>, value: False)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'reflect_padding')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'bool'>, value: False)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'penalized_mask_loss')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'bool'>, value: True)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'loss_function')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'str'>, value: mae)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'learning_rate')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'float'>, value: 5e-05)
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'model.original', option: 'lowmem')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'bool'>, value: False)
04/29/2020 12:09:05 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing ModelBase (Model): (model_dir: 'D:\Testing\faceswap\Extract\Model\model_test1', gpus: 1, configfile: None, snapshot_interval: 0, no_logs: False, warp_to_landmarks: False, augment_color: True, no_flip: False, training_image_size, 256, alignments_paths: None, preview_scale: 100, input_shape: (64, 64, 3), encoder_dim: 1024, trainer: original, pingpong: False, memory_saving_gradients: False, optimizer_savings: False, predict: True)
04/29/2020 12:09:05 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing VRAMSavings: (pingpong: False, optimizer_savings: False, memory_saving_gradients: False)
04/29/2020 12:09:05 MainProcess     MainThread      _base           set_pingpong              DEBUG    pingpong: False
04/29/2020 12:09:05 MainProcess     MainThread      _base           set_optimizer_savings     DEBUG    optimizer_savings: False
04/29/2020 12:09:05 MainProcess     MainThread      _base           set_gradient_type         DEBUG    memory_saving_gradients: False
04/29/2020 12:09:05 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized: VRAMSavings
04/29/2020 12:09:05 MainProcess     MainThread      _base           name                      DEBUG    model name: 'original'
04/29/2020 12:09:05 MainProcess     MainThread      backup_restore  __init__                  DEBUG    Initializing Backup: (model_dir: 'D:\Testing\faceswap\Extract\Model\model_test1', model_name: 'original')
04/29/2020 12:09:05 MainProcess     MainThread      backup_restore  __init__                  DEBUG    Initialized Backup
04/29/2020 12:09:05 MainProcess     MainThread      _base           name                      DEBUG    model name: 'original'
04/29/2020 12:09:05 MainProcess     MainThread      _base           config_section            DEBUG    model.original
04/29/2020 12:09:05 MainProcess     MainThread      config          __init__                  DEBUG    Initializing: Config
04/29/2020 12:09:05 MainProcess     MainThread      config          get_config_file           DEBUG    Config File location: 'D:\Testing\faceswap\config\train.ini'
04/29/2020 12:09:05 MainProcess     MainThread      _config         set_defaults              DEBUG    Setting defaults
04/29/2020 12:09:05 MainProcess     MainThread      _config         set_globals               DEBUG    Setting global config
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'global', info: 'Options that apply to all models\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'coverage', datatype: '<class 'float'>', default: '68.75', info: 'How much of the extracted image to train on. A lower coverage will limit the model's scope to a zoomed-in central area while higher amounts can include the entire face. A trade-off exists between lower amounts given more detail versus higher amounts avoiding noticeable swap transitions. Sensible values to use are:\n	62.5%% spans from eyebrow to eyebrow.\n	75.0%% spans from temple to temple.\n	87.5%% spans from ear to ear.\n	100.0%% is a mugshot.', rounding: '2', min_max: (62.5, 100.0), choices: None, gui_radio: False, fixed: True, group: face)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'mask_type', datatype: '<class 'str'>', default: 'none', info: 'The mask to be used for training. If you have selected 'Learn Mask' or 'Penalized Mask Loss' you must select a value other than 'none'. The required mask should have been selected as part of the Extract process. If it does not exist in the alignments file then it will be generated prior to training commencing.\n	none: Don't use a mask.\n	components: Mask designed to provide facial segmentation based on the positioning of landmark locations. A convex hull is constructed around the exterior of the landmarks to create a mask.\n	extended: Mask designed to provide facial segmentation based on the positioning of landmark locations. A convex hull is constructed around the exterior of the landmarks and the mask is extended upwards onto the forehead.\n	vgg-clear: Mask designed to provide smart segmentation of mostly frontal faces clear of obstructions. Profile faces and obstructions may result in sub-par performance.\n	vgg-obstructed: Mask designed to provide smart segmentation of mostly frontal faces. The mask model has been specifically trained to recognize some facial obstructions (hands and eyeglasses). Profile faces may result in sub-par performance.\n	unet-dfl: Mask designed to provide smart segmentation of mostly frontal faces. The mask model has been trained by community members and will need testing for further description. Profile faces may result in sub-par performance.', rounding: 'None', min_max: None, choices: ['none', 'components', 'extended', 'unet-dfl', 'vgg-clear', 'vgg-obstructed'], gui_radio: True, fixed: True, group: mask)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'mask_blur_kernel', datatype: '<class 'int'>', default: '3', info: 'Apply gaussian blur to the mask input. This has the effect of smoothing the edges of the mask, which can help with poorly calculated masks and give less of a hard edge to the predicted mask. The size is in pixels (calculated from a 128px mask). Set to 0 to not apply gaussian blur. This value should be odd, if an even number is passed in then it will be rounded to the next odd number.', rounding: '1', min_max: (0, 9), choices: None, gui_radio: False, fixed: True, group: mask)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'mask_threshold', datatype: '<class 'int'>', default: '4', info: 'Sets pixels that are near white to white and near black to black. Set to 0 for off.', rounding: '1', min_max: (0, 50), choices: None, gui_radio: False, fixed: True, group: mask)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'learn_mask', datatype: '<class 'bool'>', default: 'False', info: 'Dedicate a portion of the model to learning how to duplicate the input mask. Increases VRAM usage in exchange for learning a quick ability to try to replicate more complex mask models.', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: mask)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'icnr_init', datatype: '<class 'bool'>', default: 'False', info: 'Use ICNR to tile the default initializer in a repeating pattern. This strategy is designed for pairing with sub-pixel / pixel shuffler to reduce the 'checkerboard effect' in image reconstruction. \n	 https://arxiv.org/ftp/arxiv/papers/1707/1707.02937.pdf', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: initialization)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'conv_aware_init', datatype: '<class 'bool'>', default: 'False', info: 'Use Convolution Aware Initialization for convolutional layers. This can help eradicate the vanishing and exploding gradient problem as well as lead to higher accuracy, lower loss and faster convergence.\nNB:\n	 This can use more VRAM when creating a new model so you may want to lower the batch size for the first run. The batch size can be raised again when reloading the model. \n	 Multi-GPU is not supported for this option, so you should start the model on a single GPU. Once training has started, you can stop training, enable multi-GPU and resume.\n	 Building the model will likely take several minutes as the calculations for this initialization technique are expensive. This will only impact starting a new model.', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: initialization)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'subpixel_upscaling', datatype: '<class 'bool'>', default: 'False', info: 'Use subpixel upscaling rather than pixel shuffler. These techniques are both designed to produce better resolving upscaling than other methods. Each perform the same operations, but using different TF opts.\n	 https://arxiv.org/pdf/1609.05158.pdf', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'reflect_padding', datatype: '<class 'bool'>', default: 'False', info: 'Use reflection padding rather than zero padding with convolutions. Each convolution must pad the image boundaries to maintain the proper sizing. More complex padding schemes can reduce artifacts at the border of the image.\n	 http://www-cs.engr.ccny.cuny.edu/~wolberg/cs470/hw/hw2_pad.txt', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'penalized_mask_loss', datatype: '<class 'bool'>', default: 'True', info: 'Image loss function is weighted by mask presence. For areas of the image without the facial mask, reconstuction errors will be ignored while the masked face area is prioritized. May increase overall quality by focusing attention on the core face area.', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: loss)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'loss_function', datatype: '<class 'str'>', default: 'mae', info: '\n	 MAE - Mean absolute error will guide reconstructions of each pixel towards its median value in the training dataset. Robust to outliers but as a median, it can potentially ignore some infrequent image types in the dataset.\n	 MSE - Mean squared error will guide reconstructions of each pixel towards its average value in the training dataset. As an avg, it will be suspectible to outliers and typically produces slightly blurrier results.\n	 LogCosh - log(cosh(x)) acts similiar to MSE for small errors and to MAE for large errors. Like MSE, it is very stable and prevents overshoots when errors are near zero. Like MAE, it is robust to outliers.\n	 Smooth_L1 --- Modification of the MAE loss to correct two of its disadvantages. This loss has improved stability and guidance for small errors.\n	 L_inf_norm --- The L_inf norm will reduce the largest individual pixel error in an image. As each largest error is minimized sequentially, the overall error is improved. This loss will be extremely focused on outliers.\n	 SSIM - Structural Similarity Index Metric is a perception-based loss that considers changes in texture, luminance, contrast, and local spatial statistics of an image. Potentially delivers more realistic looking images.\n	 GMSD - Gradient Magnitude Similarity Deviation seeks to match the global standard deviation of the pixel to pixel differences between two images. Similiar in approach to SSIM.\n	 Pixel_Gradient_Difference - Instead of minimizing the difference between the absolute value of each pixel in two reference images, compute the pixel to pixel spatial difference in each image and then minimize that difference between two images. Allows for large color shifts,but maintains the structure of the image.\n', rounding: 'None', min_max: None, choices: ['mae', 'mse', 'logcosh', 'smooth_loss', 'l_inf_norm', 'ssim', 'gmsd', 'pixel_gradient_diff'], gui_radio: False, fixed: True, group: loss)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'global', title: 'learning_rate', datatype: '<class 'float'>', default: '5e-05', info: 'Learning rate - how fast your network will learn (how large are the modifications to the model weights after one batch of training). Values that are too large might result in model crashes and the inability of the model to find the best solution. Values that are too small might be unable to escape from dead-ends and find the best global minimum.', rounding: '6', min_max: (1e-06, 0.0001), choices: None, gui_radio: False, fixed: False, group: optimizer)
04/29/2020 12:09:05 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'train', 'model']
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: dfl_h128_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.dfl_h128_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.dfl_h128', info: 'DFL H128 Model (Adapted from https://github.com/iperov/DeepFaceLab)\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_h128', title: 'lowmem', datatype: '<class 'bool'>', default: 'False', info: 'Lower memory mode. Set to 'True' if having issues with VRAM useage.\nNB: Models with a changed lowmem mode are not compatible with each other.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.dfl_h128
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: dfl_sae_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.dfl_sae_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.dfl_sae', info: 'DFL SAE Model (Adapted from https://github.com/iperov/DeepFaceLab)\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'input_size', datatype: '<class 'int'>', default: '128', info: 'Resolution (in pixels) of the input image to train on.\nBE AWARE Larger resolution will dramatically increase VRAM requirements.\n\nMust be divisible by 16.', rounding: '16', min_max: (64, 256), choices: None, gui_radio: False, fixed: True, group: size)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'clipnorm', datatype: '<class 'bool'>', default: 'True', info: 'Controls gradient clipping of the optimizer. Can prevent model corruption at the expense of VRAM.', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: False, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'architecture', datatype: '<class 'str'>', default: 'df', info: 'Model architecture:\n	'df': Keeps the faces more natural.\n	'liae': Can help fix overly different face shapes.', rounding: 'None', min_max: None, choices: ['df', 'liae'], gui_radio: True, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'autoencoder_dims', datatype: '<class 'int'>', default: '0', info: 'Face information is stored in AutoEncoder dimensions. If there are not enough dimensions then certain facial features may not be recognized.\nHigher number of dimensions are better, but require more VRAM.\nSet to 0 to use the architecture defaults (256 for liae, 512 for df).', rounding: '32', min_max: (0, 1024), choices: None, gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'encoder_dims', datatype: '<class 'int'>', default: '42', info: 'Encoder dimensions per channel. Higher number of encoder dimensions will help the model to recognize more facial features, but will require more VRAM.', rounding: '1', min_max: (21, 85), choices: None, gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'decoder_dims', datatype: '<class 'int'>', default: '21', info: 'Decoder dimensions per channel. Higher number of decoder dimensions will help the model to improve details, but will require more VRAM.', rounding: '1', min_max: (10, 85), choices: None, gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dfl_sae', title: 'multiscale_decoder', datatype: '<class 'bool'>', default: 'False', info: 'Multiscale decoder can help to obtain better details.', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.dfl_sae
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: dlight_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.dlight_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.dlight', info: 'A lightweight, high resolution Dfaker variant (Adapted from https://github.com/dfaker/df)\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dlight', title: 'features', datatype: '<class 'str'>', default: 'best', info: 'Higher settings will allow learning more features such as tatoos, piercing,\nand wrinkles.\nStrongly affects VRAM usage.', rounding: 'None', min_max: None, choices: ['lowmem', 'fair', 'best'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dlight', title: 'details', datatype: '<class 'str'>', default: 'good', info: 'Defines detail fidelity. Lower setting can appear 'rugged' while 'good' might take onger time to train.\nAffects VRAM usage.', rounding: 'None', min_max: None, choices: ['fast', 'good'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.dlight', title: 'output_size', datatype: '<class 'int'>', default: '256', info: 'Output image resolution (in pixels).\nBe aware that larger resolution will increase VRAM requirements.\nNB: Must be either 128, 256, or 384.', rounding: '128', min_max: (128, 384), choices: [], gui_radio: False, fixed: True, group: None)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.dlight
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: original_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.original_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.original', info: 'Original Faceswap Model.\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.original', title: 'lowmem', datatype: '<class 'bool'>', default: 'False', info: 'Lower memory mode. Set to 'True' if having issues with VRAM useage.\nNB: Models with a changed lowmem mode are not compatible with each other.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.original
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: realface_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.realface_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.realface', info: 'An extra detailed variant of Original model.\nIncorporates ideas from Bryanlyon and inspiration from the Villain model.\nRequires about 6GB-8GB of VRAM (batchsize 8-16).\n\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.realface', title: 'input_size', datatype: '<class 'int'>', default: '64', info: 'Resolution (in pixels) of the input image to train on.\nBE AWARE Larger resolution will dramatically increase VRAM requirements.\nHigher resolutions may increase prediction accuracy, but does not effect the resulting output size.\nMust be between 64 and 128 and be divisible by 16.', rounding: '16', min_max: (64, 128), choices: [], gui_radio: False, fixed: True, group: size)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.realface', title: 'output_size', datatype: '<class 'int'>', default: '128', info: 'Output image resolution (in pixels).\nBe aware that larger resolution will increase VRAM requirements.\nNB: Must be between 64 and 256 and be divisible by 16.', rounding: '16', min_max: (64, 256), choices: [], gui_radio: False, fixed: True, group: size)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.realface', title: 'dense_nodes', datatype: '<class 'int'>', default: '1536', info: 'Number of nodes for decoder. Might affect your model's ability to learn in general.\nNote that: Lower values will affect the ability to predict details.', rounding: '64', min_max: (768, 2048), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.realface', title: 'complexity_encoder', datatype: '<class 'int'>', default: '128', info: 'Encoder Convolution Layer Complexity. sensible ranges: 128 to 150.', rounding: '4', min_max: (96, 160), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.realface', title: 'complexity_decoder', datatype: '<class 'int'>', default: '512', info: 'Decoder Complexity.', rounding: '4', min_max: (512, 544), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.realface
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: unbalanced_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.unbalanced_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.unbalanced', info: 'An unbalanced model with adjustable input size options.\nThis is an unbalanced model so b>a swaps may not work well\n\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'input_size', datatype: '<class 'int'>', default: '128', info: 'Resolution (in pixels) of the image to train on.\nBE AWARE Larger resolution will dramatically increaseVRAM requirements.\nMake sure your resolution is divisible by 64 (e.g. 64, 128, 256 etc.).\nNB: Your faceset must be at least 1.6x larger than your required input size.\n(e.g. 160 is the maximum input size for a 256x256 faceset).', rounding: '64', min_max: (64, 512), choices: [], gui_radio: False, fixed: True, group: size)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'lowmem', datatype: '<class 'bool'>', default: 'False', info: 'Lower memory mode. Set to 'True' if having issues with VRAM useage.\nNB: Models with a changed lowmem mode are not compatible with each other.\nNB: lowmem will override cutom nodes and complexity settings.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'clipnorm', datatype: '<class 'bool'>', default: 'True', info: 'Controls gradient clipping of the optimizer. Can prevent model corruption at the expense of VRAM.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'nodes', datatype: '<class 'int'>', default: '1024', info: 'Number of nodes for decoder. Don't change this unless you know what you are doing!', rounding: '64', min_max: (512, 4096), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'complexity_encoder', datatype: '<class 'int'>', default: '128', info: 'Encoder Convolution Layer Complexity. sensible ranges: 128 to 160.', rounding: '16', min_max: (64, 1024), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'complexity_decoder_a', datatype: '<class 'int'>', default: '384', info: 'Decoder A Complexity.', rounding: '16', min_max: (64, 1024), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.unbalanced', title: 'complexity_decoder_b', datatype: '<class 'int'>', default: '512', info: 'Decoder B Complexity.', rounding: '16', min_max: (64, 1024), choices: [], gui_radio: False, fixed: True, group: network)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.unbalanced
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: villain_defaults.py, module_path: plugins.train.model, plugin_type: model
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.villain_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'model.villain', info: 'A Higher resolution version of the Original Model by VillainGuy.\nExtremely VRAM heavy. Full model requires 9GB+ for batchsize 16\n\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'model.villain', title: 'lowmem', datatype: '<class 'bool'>', default: 'False', info: 'Lower memory mode. Set to 'True' if having issues with VRAM useage.\nNB: Models with a changed lowmem mode are not compatible with each other.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.villain
04/29/2020 12:09:05 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'train', 'trainer']
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: original_defaults.py, module_path: plugins.train.trainer, plugin_type: trainer
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.trainer.original_defaults
04/29/2020 12:09:05 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'trainer.original', info: 'Original Trainer Options.\nWARNING: The defaults for augmentation will be fine for 99.9% of use cases. Only change them if you absolutely know what you are doing!')
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'preview_images', datatype: '<class 'int'>', default: '14', info: 'Number of sample faces to display for each side in the preview when training.', rounding: '2', min_max: (2, 16), choices: None, gui_radio: False, fixed: True, group: evaluation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'zoom_amount', datatype: '<class 'int'>', default: '5', info: 'Percentage amount to randomly zoom each training image in and out.', rounding: '1', min_max: (0, 25), choices: None, gui_radio: False, fixed: True, group: image augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'rotation_range', datatype: '<class 'int'>', default: '10', info: 'Percentage amount to randomly rotate each training image.', rounding: '1', min_max: (0, 25), choices: None, gui_radio: False, fixed: True, group: image augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'shift_range', datatype: '<class 'int'>', default: '5', info: 'Percentage amount to randomly shift each training image horizontally and vertically.', rounding: '1', min_max: (0, 25), choices: None, gui_radio: False, fixed: True, group: image augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'flip_chance', datatype: '<class 'int'>', default: '50', info: 'Percentage chance to randomly flip each training image horizontally.\nNB: This is ignored if the 'no-flip' option is enabled', rounding: '1', min_max: (0, 75), choices: None, gui_radio: False, fixed: True, group: image augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'color_lightness', datatype: '<class 'int'>', default: '30', info: 'Percentage amount to randomly alter the lightness of each training image.\nNB: This is ignored if the 'no-augment-color' option is enabled', rounding: '1', min_max: (0, 75), choices: None, gui_radio: False, fixed: True, group: color augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'color_ab', datatype: '<class 'int'>', default: '8', info: 'Percentage amount to randomly alter the 'a' and 'b' colors of the L*a*b* color space of each training image.\nNB: This is ignored if the 'no-augment-color' option is enabled', rounding: '1', min_max: (0, 50), choices: None, gui_radio: False, fixed: True, group: color augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'color_clahe_chance', datatype: '<class 'int'>', default: '50', info: 'Percentage chance to perform Contrast Limited Adaptive Histogram Equalization on each training image.\nNB: This is ignored if the 'no-augment-color' option is enabled', rounding: '1', min_max: (0, 75), choices: None, gui_radio: False, fixed: False, group: color augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'color_clahe_max_size', datatype: '<class 'int'>', default: '4', info: 'The grid size dictates how much Contrast Limited Adaptive Histogram Equalization is performed on any training image selected for clahe. Contrast will be applied randomly with a gridsize of 0 up to the maximum. This value is a multiplier calculated from the training image size.\nNB: This is ignored if the 'no-augment-color' option is enabled', rounding: '1', min_max: (1, 8), choices: None, gui_radio: False, fixed: True, group: color augmentation)
04/29/2020 12:09:05 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: trainer.original
04/29/2020 12:09:05 MainProcess     MainThread      config          handle_config             DEBUG    Handling config
04/29/2020 12:09:05 MainProcess     MainThread      config          check_exists              DEBUG    Config file exists: 'D:\Testing\faceswap\config\train.ini'
04/29/2020 12:09:05 MainProcess     MainThread      config          load_config               VERBOSE  Loading config: 'D:\Testing\faceswap\config\train.ini'
04/29/2020 12:09:05 MainProcess     MainThread      config          validate_config           DEBUG    Validating config
04/29/2020 12:09:05 MainProcess     MainThread      config          check_config_change       DEBUG    Default config has not changed
04/29/2020 12:09:05 MainProcess     MainThread      config          check_config_choices      DEBUG    Checking config choices
04/29/2020 12:09:05 MainProcess     MainThread      config          check_config_choices      DEBUG    Checked config choices
04/29/2020 12:09:05 MainProcess     MainThread      config          validate_config           DEBUG    Validated config
04/29/2020 12:09:05 MainProcess     MainThread      config          handle_config             DEBUG    Handled config
04/29/2020 12:09:05 MainProcess     MainThread      config          __init__                  DEBUG    Initialized: Config
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'learning_rate')
04/29/2020 12:09:05 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'float'>, value: 5e-05)
04/29/2020 12:09:05 MainProcess     MainThread      config          changeable_items          DEBUG    Alterable for existing models: {'learning_rate': 5e-05}
04/29/2020 12:09:05 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing State: (model_dir: 'D:\Testing\faceswap\Extract\Model\model_test1', model_name: 'original', config_changeable_items: '{'learning_rate': 5e-05}', no_logs: False, pingpong: False, training_image_size: '256'
04/29/2020 12:09:05 MainProcess     MainThread      serializer      get_serializer            DEBUG    <lib.serializer._JSONSerializer object at 0x00000260F57CEA08>
04/29/2020 12:09:05 MainProcess     MainThread      _base           load                      DEBUG    Loading State
04/29/2020 12:09:05 MainProcess     MainThread      serializer      load                      DEBUG    filename: D:\Testing\faceswap\Extract\Model\model_test1\original_state.json
04/29/2020 12:09:05 MainProcess     MainThread      serializer      load                      DEBUG    stored data type: <class 'bytes'>
04/29/2020 12:09:05 MainProcess     MainThread      serializer      unmarshal                 DEBUG    data type: <class 'bytes'>
04/29/2020 12:09:05 MainProcess     MainThread      serializer      unmarshal                 DEBUG    returned data type: <class 'dict'>
04/29/2020 12:09:05 MainProcess     MainThread      serializer      load                      DEBUG    data type: <class 'dict'>
04/29/2020 12:09:05 MainProcess     MainThread      _base           load                      DEBUG    Loaded state: {'name': 'original', 'sessions': {'1': {'timestamp': 1588069963.2956283, 'no_logs': False, 'pingpong': False, 'loss_names': {'a': ['face_loss'], 'b': ['face_loss']}, 'batchsize': 64, 'iterations': 40695, 'config': {'learning_rate': 5e-05}}, '2': {'timestamp': 1588096724.7223222, 'no_logs': False, 'pingpong': False, 'loss_names': {'a': ['face_loss'], 'b': ['face_loss']}, 'batchsize': 64, 'iterations': 16356, 'config': {'learning_rate': 5e-05}}, '3': {'timestamp': 1588107762.301436, 'no_logs': False, 'pingpong': False, 'loss_names': {'a': ['face_loss'], 'b': ['face_loss']}, 'batchsize': 64, 'iterations': 56219, 'config': {'learning_rate': 5e-05}}, '4': {'timestamp': 1588143644.5661523, 'no_logs': False, 'pingpong': False, 'loss_names': {'a': ['face_loss'], 'b': ['face_loss']}, 'batchsize': 64, 'iterations': 4831, 'config': {'learning_rate': 5e-05}}, '5': {'timestamp': 1588146750.5387857, 'no_logs': False, 'pingpong': False, 'loss_names': {'a': ['face_loss'], 'b': ['face_loss']}, 'batchsize': 64, 'iterations': 14460, 'config': {'learning_rate': 5e-05}}}, 'lowest_avg_loss': {'a': 0.03463127989321947, 'b': 0.02329189281910658}, 'iterations': 132561, 'inputs': {'face_in:0': [64, 64, 3]}, 'training_size': 256, 'config': {'coverage': 68.75, 'mask_type': None, 'mask_blur_kernel': 3, 'mask_threshold': 4, 'learn_mask': False, 'icnr_init': False, 'conv_aware_init': False, 'subpixel_upscaling': False, 'reflect_padding': False, 'penalized_mask_loss': True, 'loss_function': 'mae', 'learning_rate': 5e-05, 'lowmem': False}}
04/29/2020 12:09:05 MainProcess     MainThread      _base           _update_legacy_config     DEBUG    Checking for legacy state file update
04/29/2020 12:09:05 MainProcess     MainThread      _base           _update_legacy_config     DEBUG    Legacy item 'dssim_loss' not in config. Skipping update
04/29/2020 12:09:05 MainProcess     MainThread      _base           _update_legacy_config     DEBUG    State file updated for legacy config: False
04/29/2020 12:09:05 MainProcess     MainThread      _base           replace_config            DEBUG    Replacing config. Old config: {'coverage': 68.75, 'mask_type': None, 'mask_blur_kernel': 3, 'mask_threshold': 4, 'learn_mask': False, 'icnr_init': False, 'conv_aware_init': False, 'subpixel_upscaling': False, 'reflect_padding': False, 'penalized_mask_loss': True, 'loss_function': 'mae', 'learning_rate': 5e-05, 'lowmem': False}
04/29/2020 12:09:05 MainProcess     MainThread      _base           replace_config            DEBUG    Replaced config. New config: {'coverage': 68.75, 'mask_type': None, 'mask_blur_kernel': 3, 'mask_threshold': 4, 'learn_mask': False, 'icnr_init': False, 'conv_aware_init': False, 'subpixel_upscaling': False, 'reflect_padding': False, 'penalized_mask_loss': True, 'loss_function': 'mae', 'learning_rate': 5e-05, 'lowmem': False}
04/29/2020 12:09:05 MainProcess     MainThread      _base           replace_config            INFO     Using configuration saved in state file
04/29/2020 12:09:05 MainProcess     MainThread      _base           new_session_id            DEBUG    6
04/29/2020 12:09:05 MainProcess     MainThread      _base           create_new_session        DEBUG    Creating new session. id: 6
04/29/2020 12:09:05 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized State:
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       __init__                  DEBUG    Initializing NNBlocks: (use_subpixel: False, use_icnr_init: False, use_convaware_init: False, use_reflect_padding: False, first_run: False)
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       __init__                  DEBUG    Initialized NNBlocks
04/29/2020 12:09:05 MainProcess     MainThread      _base           name                      DEBUG    model name: 'original'
04/29/2020 12:09:05 MainProcess     MainThread      _base           rename_legacy             DEBUG    Renaming legacy files
04/29/2020 12:09:05 MainProcess     MainThread      _base           name                      DEBUG    model name: 'original'
04/29/2020 12:09:05 MainProcess     MainThread      _base           rename_legacy             DEBUG    No legacy files to rename
04/29/2020 12:09:05 MainProcess     MainThread      _base           load_state_info           DEBUG    Loading Input Shape from State file
04/29/2020 12:09:05 MainProcess     MainThread      _base           load_state_info           DEBUG    Setting input shape from state file: (64, 64, 3)
04/29/2020 12:09:05 MainProcess     MainThread      _base           calculate_coverage_ratio  DEBUG    Requested coverage_ratio: 0.6875
04/29/2020 12:09:05 MainProcess     MainThread      _base           calculate_coverage_ratio  DEBUG    Final coverage_ratio: 0.6875
04/29/2020 12:09:05 MainProcess     MainThread      _base           __init__                  DEBUG    training_opts: {'alignments': None, 'preview_scaling': 1.0, 'warp_to_landmarks': False, 'augment_color': True, 'no_flip': False, 'pingpong': False, 'snapshot_interval': 0, 'training_size': 256, 'no_logs': False, 'coverage_ratio': 0.6875, 'mask_type': None, 'mask_blur_kernel': 3, 'mask_threshold': 4, 'learn_mask': False, 'penalized_mask_loss': False}
04/29/2020 12:09:05 MainProcess     MainThread      _base           multiple_models_in_folder DEBUG    model_files: ['original_decoder_A.h5', 'original_decoder_B.h5', 'original_encoder.h5'], retval: False
04/29/2020 12:09:05 MainProcess     MainThread      original        add_networks              DEBUG    Adding networks
04/29/2020 12:09:05 MainProcess     MainThread      module_wrapper  _tfmw_add_deprecation_warning DEBUG    From D:\MiniConda\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:74: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n
04/29/2020 12:09:05 MainProcess     MainThread      module_wrapper  _tfmw_add_deprecation_warning DEBUG    From D:\MiniConda\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.\n
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       upscale                   DEBUG    inp: Tensor("input_1:0", shape=(?, 8, 8, 512), dtype=float32), filters: 256, kernel_size: 3, use_instance_norm: False, kwargs: {})
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       get_name                  DEBUG    Generating block name: upscale_8_0
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x00000260F57ED388>
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       conv2d                    DEBUG    inp: Tensor("input_1:0", shape=(?, 8, 8, 512), dtype=float32), filters: 1024, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_8_0_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x00000260F57ED388>})
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Using model specified initializer: <keras.initializers.VarianceScaling object at 0x00000260F57ED388>
04/29/2020 12:09:05 MainProcess     MainThread      module_wrapper  _tfmw_add_deprecation_warning DEBUG    From D:\MiniConda\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.\n
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       upscale                   DEBUG    inp: Tensor("upscale_8_0_pixelshuffler/Reshape_1:0", shape=(?, 16, 16, 256), dtype=float32), filters: 128, kernel_size: 3, use_instance_norm: False, kwargs: {})
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       get_name                  DEBUG    Generating block name: upscale_16_0
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x00000260F582BA88>
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       conv2d                    DEBUG    inp: Tensor("upscale_8_0_pixelshuffler/Reshape_1:0", shape=(?, 16, 16, 256), dtype=float32), filters: 512, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_16_0_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x00000260F582BA88>})
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Using model specified initializer: <keras.initializers.VarianceScaling object at 0x00000260F582BA88>
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       upscale                   DEBUG    inp: Tensor("upscale_16_0_pixelshuffler/Reshape_1:0", shape=(?, 32, 32, 128), dtype=float32), filters: 64, kernel_size: 3, use_instance_norm: False, kwargs: {})
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       get_name                  DEBUG    Generating block name: upscale_32_0
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x00000260F5842708>
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       conv2d                    DEBUG    inp: Tensor("upscale_16_0_pixelshuffler/Reshape_1:0", shape=(?, 32, 32, 128), dtype=float32), filters: 256, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_32_0_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x00000260F5842708>})
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Using model specified initializer: <keras.initializers.VarianceScaling object at 0x00000260F5842708>
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       conv2d                    DEBUG    inp: Tensor("upscale_32_0_pixelshuffler/Reshape_1:0", shape=(?, 64, 64, 64), dtype=float32), filters: 3, kernel_size: 5, strides: (1, 1), padding: same, kwargs: {'activation': 'sigmoid', 'name': 'face_out'})
04/29/2020 12:09:05 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x00000260F5842AC8>
04/29/2020 12:09:05 MainProcess     MainThread      _base           add_network               DEBUG    network_type: 'decoder', side: 'a', network: '<keras.engine.training.Model object at 0x00000260F5996848>', is_output: True
04/29/2020 12:09:05 MainProcess     MainThread      _base           name                      DEBUG    model name: 'original'
04/29/2020 12:09:05 MainProcess     MainThread      _base           add_network               DEBUG    name: 'decoder_a', filename: 'original_decoder_A.h5'
04/29/2020 12:09:05 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing NNMeta: (filename: 'D:\Testing\faceswap\Extract\Model\model_test1\original_decoder_A.h5', network_type: 'decoder', side: 'a', network: <keras.engine.training.Model object at 0x00000260F5996848>, is_output: True
04/29/2020 12:09:05 MainProcess     MainThread      module_wrapper  _tfmw_add_deprecation_warning DEBUG    From D:\MiniConda\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:174: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.\n
04/29/2020 12:09:05 MainProcess     MainThread      module_wrapper  _tfmw_add_deprecation_warning DEBUG    From D:\MiniConda\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:181: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.\n
04/29/2020 12:09:05 MainProcess     MainThread      module_wrapper  _tfmw_add_deprecation_warning DEBUG    From D:\MiniConda\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:186: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.\n
04/29/2020 12:09:06 MainProcess     MainThread      module_wrapper  _tfmw_add_deprecation_warning DEBUG    From D:\MiniConda\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:190: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.\n
04/29/2020 12:09:06 MainProcess     MainThread      module_wrapper  _tfmw_add_deprecation_warning DEBUG    From D:\MiniConda\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:199: The name tf.is_variable_initialized is deprecated. Please use tf.compat.v1.is_variable_initialized instead.\n
04/29/2020 12:09:06 MainProcess     MainThread      module_wrapper  _tfmw_add_deprecation_warning DEBUG    From D:\MiniConda\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:206: The name tf.variables_initializer is deprecated. Please use tf.compat.v1.variables_initializer instead.\n
04/29/2020 12:09:06 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized NNMeta
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       upscale                   DEBUG    inp: Tensor("input_2:0", shape=(?, 8, 8, 512), dtype=float32), filters: 256, kernel_size: 3, use_instance_norm: False, kwargs: {})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       get_name                  DEBUG    Generating block name: upscale_8_1
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x00000260F575EA88>
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       conv2d                    DEBUG    inp: Tensor("input_2:0", shape=(?, 8, 8, 512), dtype=float32), filters: 1024, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_8_1_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x00000260F575EA88>})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Using model specified initializer: <keras.initializers.VarianceScaling object at 0x00000260F575EA88>
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       upscale                   DEBUG    inp: Tensor("upscale_8_1_pixelshuffler/Reshape_1:0", shape=(?, 16, 16, 256), dtype=float32), filters: 128, kernel_size: 3, use_instance_norm: False, kwargs: {})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       get_name                  DEBUG    Generating block name: upscale_16_1
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x00000260F59C1C48>
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       conv2d                    DEBUG    inp: Tensor("upscale_8_1_pixelshuffler/Reshape_1:0", shape=(?, 16, 16, 256), dtype=float32), filters: 512, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_16_1_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x00000260F59C1C48>})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Using model specified initializer: <keras.initializers.VarianceScaling object at 0x00000260F59C1C48>
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       upscale                   DEBUG    inp: Tensor("upscale_16_1_pixelshuffler/Reshape_1:0", shape=(?, 32, 32, 128), dtype=float32), filters: 64, kernel_size: 3, use_instance_norm: False, kwargs: {})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       get_name                  DEBUG    Generating block name: upscale_32_1
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x00000260F59C9F08>
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       conv2d                    DEBUG    inp: Tensor("upscale_16_1_pixelshuffler/Reshape_1:0", shape=(?, 32, 32, 128), dtype=float32), filters: 256, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_32_1_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x00000260F59C9F08>})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Using model specified initializer: <keras.initializers.VarianceScaling object at 0x00000260F59C9F08>
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       conv2d                    DEBUG    inp: Tensor("upscale_32_1_pixelshuffler/Reshape_1:0", shape=(?, 64, 64, 64), dtype=float32), filters: 3, kernel_size: 5, strides: (1, 1), padding: same, kwargs: {'activation': 'sigmoid', 'name': 'face_out'})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x00000260F59C9E48>
04/29/2020 12:09:06 MainProcess     MainThread      _base           add_network               DEBUG    network_type: 'decoder', side: 'b', network: '<keras.engine.training.Model object at 0x00000260E7ED0588>', is_output: True
04/29/2020 12:09:06 MainProcess     MainThread      _base           name                      DEBUG    model name: 'original'
04/29/2020 12:09:06 MainProcess     MainThread      _base           add_network               DEBUG    name: 'decoder_b', filename: 'original_decoder_B.h5'
04/29/2020 12:09:06 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing NNMeta: (filename: 'D:\Testing\faceswap\Extract\Model\model_test1\original_decoder_B.h5', network_type: 'decoder', side: 'b', network: <keras.engine.training.Model object at 0x00000260E7ED0588>, is_output: True
04/29/2020 12:09:06 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized NNMeta
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       conv                      DEBUG    inp: Tensor("input_3:0", shape=(?, 64, 64, 3), dtype=float32), filters: 128, kernel_size: 5, strides: 2, use_instance_norm: False, kwargs: {})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       get_name                  DEBUG    Generating block name: conv_64_0
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       conv2d                    DEBUG    inp: Tensor("input_3:0", shape=(?, 64, 64, 3), dtype=float32), filters: 128, kernel_size: 5, strides: 2, padding: same, kwargs: {'name': 'conv_64_0_conv2d'})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x00000260E7EE5E88>
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       conv                      DEBUG    inp: Tensor("conv_64_0_leakyrelu/LeakyRelu:0", shape=(?, 32, 32, 128), dtype=float32), filters: 256, kernel_size: 5, strides: 2, use_instance_norm: False, kwargs: {})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       get_name                  DEBUG    Generating block name: conv_32_0
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       conv2d                    DEBUG    inp: Tensor("conv_64_0_leakyrelu/LeakyRelu:0", shape=(?, 32, 32, 128), dtype=float32), filters: 256, kernel_size: 5, strides: 2, padding: same, kwargs: {'name': 'conv_32_0_conv2d'})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x00000260E7EE5D48>
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       conv                      DEBUG    inp: Tensor("conv_32_0_leakyrelu/LeakyRelu:0", shape=(?, 16, 16, 256), dtype=float32), filters: 512, kernel_size: 5, strides: 2, use_instance_norm: False, kwargs: {})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       get_name                  DEBUG    Generating block name: conv_16_0
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       conv2d                    DEBUG    inp: Tensor("conv_32_0_leakyrelu/LeakyRelu:0", shape=(?, 16, 16, 256), dtype=float32), filters: 512, kernel_size: 5, strides: 2, padding: same, kwargs: {'name': 'conv_16_0_conv2d'})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x00000260E7EEA788>
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       conv                      DEBUG    inp: Tensor("conv_16_0_leakyrelu/LeakyRelu:0", shape=(?, 8, 8, 512), dtype=float32), filters: 1024, kernel_size: 5, strides: 2, use_instance_norm: False, kwargs: {})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       get_name                  DEBUG    Generating block name: conv_8_0
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       conv2d                    DEBUG    inp: Tensor("conv_16_0_leakyrelu/LeakyRelu:0", shape=(?, 8, 8, 512), dtype=float32), filters: 1024, kernel_size: 5, strides: 2, padding: same, kwargs: {'name': 'conv_8_0_conv2d'})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x00000260E8FE3A08>
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       upscale                   DEBUG    inp: Tensor("reshape_1/Reshape:0", shape=(?, 4, 4, 1024), dtype=float32), filters: 512, kernel_size: 3, use_instance_norm: False, kwargs: {})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       get_name                  DEBUG    Generating block name: upscale_4_0
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x00000260F57EDBC8>
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       conv2d                    DEBUG    inp: Tensor("reshape_1/Reshape:0", shape=(?, 4, 4, 1024), dtype=float32), filters: 2048, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_4_0_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x00000260F57EDBC8>})
04/29/2020 12:09:06 MainProcess     MainThread      nn_blocks       set_default_initializer   DEBUG    Using model specified initializer: <keras.initializers.VarianceScaling object at 0x00000260F57EDBC8>
04/29/2020 12:09:06 MainProcess     MainThread      _base           add_network               DEBUG    network_type: 'encoder', side: 'None', network: '<keras.engine.training.Model object at 0x00000260F57F4A08>', is_output: False
04/29/2020 12:09:06 MainProcess     MainThread      _base           name                      DEBUG    model name: 'original'
04/29/2020 12:09:06 MainProcess     MainThread      _base           add_network               DEBUG    name: 'encoder', filename: 'original_encoder.h5'
04/29/2020 12:09:06 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing NNMeta: (filename: 'D:\Testing\faceswap\Extract\Model\model_test1\original_encoder.h5', network_type: 'encoder', side: 'None', network: <keras.engine.training.Model object at 0x00000260F57F4A08>, is_output: False
04/29/2020 12:09:06 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized NNMeta
04/29/2020 12:09:06 MainProcess     MainThread      original        add_networks              DEBUG    Added networks
04/29/2020 12:09:06 MainProcess     MainThread      _base           load_models               DEBUG    Load model: (swapped: False)
04/29/2020 12:09:06 MainProcess     MainThread      _base           models_exist              DEBUG    Pre-existing models exist: True
04/29/2020 12:09:06 MainProcess     MainThread      _base           models_exist              DEBUG    Pre-existing models exist: True
04/29/2020 12:09:06 MainProcess     MainThread      module_wrapper  _tfmw_add_deprecation_warning DEBUG    From D:\MiniConda\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:95: The name tf.reset_default_graph is deprecated. Please use tf.compat.v1.reset_default_graph instead.\n
04/29/2020 12:09:06 MainProcess     MainThread      module_wrapper  _tfmw_add_deprecation_warning DEBUG    From D:\MiniConda\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:98: The name tf.placeholder_with_default is deprecated. Please use tf.compat.v1.placeholder_with_default instead.\n
04/29/2020 12:09:07 MainProcess     MainThread      _base           map_models                DEBUG    Map models: (swapped: False)
04/29/2020 12:09:07 MainProcess     MainThread      _base           map_models                DEBUG    Mapped models: (models_map: {'a': {'decoder': 'D:\\Testing\\faceswap\\Extract\\Model\\model_test1\\original_decoder_A.h5'}, 'b': {'decoder': 'D:\\Testing\\faceswap\\Extract\\Model\\model_test1\\original_decoder_B.h5'}})
04/29/2020 12:09:07 MainProcess     MainThread      _base           load                      DEBUG    Loading model: 'D:\Testing\faceswap\Extract\Model\model_test1\original_decoder_A.h5'
04/29/2020 12:09:07 MainProcess     MainThread      _base           load                      DEBUG    Loading model: 'D:\Testing\faceswap\Extract\Model\model_test1\original_decoder_B.h5'
04/29/2020 12:09:07 MainProcess     MainThread      _base           load                      DEBUG    Loading model: 'D:\Testing\faceswap\Extract\Model\model_test1\original_encoder.h5'
04/29/2020 12:09:07 MainProcess     MainThread      _base           load_models               INFO     Loaded model from disk: 'D:\Testing\faceswap\Extract\Model\model_test1'
04/29/2020 12:09:07 MainProcess     MainThread      _base           get_inputs                DEBUG    Getting inputs
04/29/2020 12:09:07 MainProcess     MainThread      _base           get_inputs                DEBUG    Got inputs: [<tf.Tensor 'face_in:0' shape=(?, 64, 64, 3) dtype=float32>]
04/29/2020 12:09:07 MainProcess     MainThread      original        build_autoencoders        DEBUG    Initializing model
04/29/2020 12:09:07 MainProcess     MainThread      original        build_autoencoders        DEBUG    Adding Autoencoder. Side: a
04/29/2020 12:09:07 MainProcess     MainThread      _base           add_predictor             DEBUG    Adding predictor: (side: 'a', model: <keras.engine.training.Model object at 0x00000260E9035588>)
04/29/2020 12:09:07 MainProcess     MainThread      original        build_autoencoders        DEBUG    Adding Autoencoder. Side: b
04/29/2020 12:09:07 MainProcess     MainThread      _base           add_predictor             DEBUG    Adding predictor: (side: 'b', model: <keras.engine.training.Model object at 0x00000260FBD4F708>)
04/29/2020 12:09:07 MainProcess     MainThread      original        build_autoencoders        DEBUG    Initialized model
04/29/2020 12:09:07 MainProcess     MainThread      _base           compile_predictors        DEBUG    Compiling Predictors
04/29/2020 12:09:07 MainProcess     MainThread      _base           get_optimizer             DEBUG    Optimizer kwargs: {'lr': 5e-05, 'beta_1': 0.5, 'beta_2': 0.999}
04/29/2020 12:09:07 MainProcess     MainThread      optimizers      set_cpu_mode              DEBUG    Optimizer CPU Mode set to False
04/29/2020 12:09:07 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing Loss: (inputs: [<tf.Tensor 'face_in:0' shape=(?, 64, 64, 3) dtype=float32>], outputs: [<tf.Tensor 'decoder_a/face_out/Sigmoid:0' shape=(?, 64, 64, 3) dtype=float32>])
04/29/2020 12:09:07 MainProcess     MainThread      _base           get_loss_names            DEBUG    Model output names: ['decoder_a/face_out/Sigmoid:0']
04/29/2020 12:09:07 MainProcess     MainThread      _base           get_loss_names            DEBUG    ['face_loss']
04/29/2020 12:09:07 MainProcess     MainThread      _base           selected_loss             DEBUG    <function mean_absolute_error at 0x00000260F42380D8>
04/29/2020 12:09:07 MainProcess     MainThread      _base           get_loss_functions        DEBUG    face_loss: <function mean_absolute_error at 0x00000260F42380D8>
04/29/2020 12:09:07 MainProcess     MainThread      _base           get_loss_functions        DEBUG    [<function mean_absolute_error at 0x00000260F42380D8>]
04/29/2020 12:09:07 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized: Loss
04/29/2020 12:09:07 MainProcess     MainThread      module_wrapper  _tfmw_add_deprecation_warning DEBUG    From D:\MiniConda\envs\faceswap\lib\site-packages\keras\optimizers.py:790: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n
04/29/2020 12:09:07 MainProcess     MainThread      _base           add_session_loss_names    DEBUG    Adding session loss_names. (side: 'a', loss_names: ['face_loss']
04/29/2020 12:09:07 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing Loss: (inputs: [<tf.Tensor 'face_in:0' shape=(?, 64, 64, 3) dtype=float32>], outputs: [<tf.Tensor 'decoder_b/face_out/Sigmoid:0' shape=(?, 64, 64, 3) dtype=float32>])
04/29/2020 12:09:07 MainProcess     MainThread      _base           get_loss_names            DEBUG    Model output names: ['decoder_b/face_out/Sigmoid:0']
04/29/2020 12:09:07 MainProcess     MainThread      _base           get_loss_names            DEBUG    ['face_loss']
04/29/2020 12:09:07 MainProcess     MainThread      _base           selected_loss             DEBUG    <function mean_absolute_error at 0x00000260F42380D8>
04/29/2020 12:09:07 MainProcess     MainThread      _base           get_loss_functions        DEBUG    face_loss: <function mean_absolute_error at 0x00000260F42380D8>
04/29/2020 12:09:07 MainProcess     MainThread      _base           get_loss_functions        DEBUG    [<function mean_absolute_error at 0x00000260F42380D8>]
04/29/2020 12:09:07 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized: Loss
04/29/2020 12:09:07 MainProcess     MainThread      _base           add_session_loss_names    DEBUG    Adding session loss_names. (side: 'b', loss_names: ['face_loss']
04/29/2020 12:09:07 MainProcess     MainThread      _base           compile_predictors        DEBUG    Compiled Predictors. Losses: ['face_loss']
04/29/2020 12:09:07 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized ModelBase (Model)
04/29/2020 12:09:07 MainProcess     MainThread      original        __init__                  DEBUG    Initialized Model
04/29/2020 12:09:07 MainProcess     MainThread      convert         _load_model               DEBUG    Loaded Model
04/29/2020 12:09:07 MainProcess     MainThread      _base           largest_face_index        DEBUG    0
04/29/2020 12:09:07 MainProcess     MainThread      _base           converter                 DEBUG    Getting Converter: (swap: False)
04/29/2020 12:09:07 MainProcess     MainThread      _base           converter                 DEBUG    Got Converter: <bound method Model.predict of <keras.engine.training.Model object at 0x00000260FBD4F708>>
04/29/2020 12:09:07 MainProcess     MainThread      multithreading  __init__                  DEBUG    Initializing MultiThread: (target: '_predict_faces', thread_count: 1)
04/29/2020 12:09:07 MainProcess     MainThread      multithreading  __init__                  TRACE    args: (), kwargs: {}
04/29/2020 12:09:07 MainProcess     MainThread      multithreading  __init__                  DEBUG    Initialized MultiThread: '_predict_faces'
04/29/2020 12:09:07 MainProcess     MainThread      multithreading  start                     DEBUG    Starting thread(s): '_predict_faces'
04/29/2020 12:09:07 MainProcess     MainThread      multithreading  start                     DEBUG    Starting thread 1 of 1: '_predict_faces_0'
04/29/2020 12:09:07 MainProcess     _predict_faces_0 convert         _predict_faces            DEBUG    EOF Received
04/29/2020 12:09:07 MainProcess     MainThread      multithreading  start                     DEBUG    Started all threads '_predict_faces': 1
04/29/2020 12:09:07 MainProcess     _predict_faces_0 convert         _predict_faces            DEBUG    Putting EOF
04/29/2020 12:09:07 MainProcess     MainThread      convert         __init__                  DEBUG    Initialized Predict: (out_queue: <queue.Queue object at 0x00000260F5983788>)
04/29/2020 12:09:07 MainProcess     _predict_faces_0 convert         _predict_faces            DEBUG    Load queue complete
04/29/2020 12:09:07 MainProcess     MainThread      utils           get_folder                DEBUG    Requested path: 'D:\Testing\faceswap\Extract\Convert\test2'
04/29/2020 12:09:07 MainProcess     MainThread      utils           get_folder                DEBUG    Returning: 'D:\Testing\faceswap\Extract\Convert\test2'
04/29/2020 12:09:07 MainProcess     MainThread      _base           largest_face_index        DEBUG    0
04/29/2020 12:09:07 MainProcess     MainThread      opencv          pre_encode                TRACE    Pre-encoding image
04/29/2020 12:09:07 MainProcess     MainThread      convert         pre_encode                DEBUG    Writer pre_encode function: <bound method Writer.pre_encode of <plugins.convert.writer.opencv.Writer object at 0x00000260F44B5148>>
04/29/2020 12:09:07 MainProcess     MainThread      convert         __init__                  DEBUG    Initializing Converter: (output_size: 64,  coverage_ratio: 0.6875, draw_transparent: False, pre_encode: <bound method Writer.pre_encode of <plugins.convert.writer.opencv.Writer object at 0x00000260F44B5148>>, arguments: Namespace(alignments_path='D:\\Testing\\faceswap\\Extract\\Source\\source_test1\\source_test1\\alignments.fsa', allow_growth=False, colab=False, color_adjustment='avg-color', configfile=None, filter=None, frame_ranges=None, func=<bound method ScriptExecutor.execute_script of <lib.cli.launcher.ScriptExecutor object at 0x00000260EB9D09C8>>, gpus=1, input_aligned_dir=None, input_dir='D:\\Testing\\faceswap\\Extract\\Source\\source_test1', jobs=0, keep_unchanged=False, logfile='D:\\Testing\\faceswap\\Extract\\log_test1.log', loglevel='TRACE', mask_type='none', model_dir='D:\\Testing\\faceswap\\Extract\\Model\\model_test1', nfilter=None, on_the_fly=False, output_dir='D:\\Testing\\faceswap\\Extract\\Convert\\test2', output_scale=100, redirect_gui=True, ref_threshold=0.4, reference_video=None, scaling='none', singleprocess=False, swap_model=False, trainer=None, writer='opencv'), configfile: None)
04/29/2020 12:09:07 MainProcess     MainThread      convert         _load_plugins             DEBUG    Loading plugins. config: None
04/29/2020 12:09:07 MainProcess     MainThread      plugin_loader   _import                   INFO     Loading Mask from Box_Blend plugin...
04/29/2020 12:09:07 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing Mask: (arguments: 'none', output_size: 64, configfile: None, config: None)
04/29/2020 12:09:07 MainProcess     MainThread      config          __init__                  DEBUG    Initializing: Config
04/29/2020 12:09:07 MainProcess     MainThread      config          get_config_file           DEBUG    Config File location: 'D:\Testing\faceswap\config\convert.ini'
04/29/2020 12:09:07 MainProcess     MainThread      _config         set_defaults              DEBUG    Setting defaults
04/29/2020 12:09:07 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'color']
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: color_transfer_defaults.py, module_path: plugins.convert.color, plugin_type: color
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.color.color_transfer_defaults
04/29/2020 12:09:07 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'color.color_transfer', info: 'Options for transfering the color distribution from the source to the target image using the mean and standard deviations of the L*a*b* color space.\nThis implementation is (loosely) based on the 'Color Transfer between Images' paper by Reinhard et al., 2001. matching the histograms between the source and destination faces.')
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.color_transfer', title: 'clip', datatype: '<class 'bool'>', default: 'True', info: 'Should components of L*a*b* image be scaled by np.clip before converting back to BGR color space?\nIf False then components will be min-max scaled appropriately.\nClipping will keep target image brightness truer to the input.\nScaling will adjust image brightness to avoid washed out portions in the resulting color transfer that can be caused by clipping.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: method)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.color_transfer', title: 'preserve_paper', datatype: '<class 'bool'>', default: 'True', info: 'Should color transfer strictly follow methodology layed out in original paper?\nThe method does not always produce aesthetically pleasing results.\nIf False then L*a*b* components will be scaled using the reciprocal of the scaling factor proposed in the paper. This method seems to produce more consistently aesthetically pleasing results.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: method)
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: color.color_transfer
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: manual_balance_defaults.py, module_path: plugins.convert.color, plugin_type: color
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.color.manual_balance_defaults
04/29/2020 12:09:07 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'color.manual_balance', info: 'Options for manually altering the balance of colors of the swapped face')
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'colorspace', datatype: '<class 'str'>', default: 'HSV', info: 'The colorspace to use for adjustment: The three adjustment sliders will effect the image differently depending on which colorspace is selected:\n	 RGB: Red, Green, Blue. An additive colorspace where colors are obtained by a linear combination of Red, Green, and Blue values. The three channels are correlated by the amount of light hitting the surface. In RGB color space the color information is separated into three channels but the same three channels also encode brightness information.\n	 HSV: Hue, Saturation, Value. Hue - Dominant wavelength. Saturation - Purity / shades of color. Value - Intensity. Best thing is that it uses only one channel to describe color (H), making it very intuitive to specify color.\n	 LAB: Lightness, A, B. Lightness - Intensity. A - Color range from green to magenta. B - Color range from blue to yellow. The L channel is independent of color information and encodes brightness only. The other two channels encode color.\n	 YCrCb: Y - Luminance or Luma component obtained from RGB after gamma correction. Cr - how far is the red component from Luma. Cb - how far is the blue component from Luma. Separates the luminance and chrominance components into different channels.', rounding: 'None', min_max: None, choices: ['RGB', 'HSV', 'LAB', 'YCrCb'], gui_radio: True, fixed: True, group: color balance)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'balance_1', datatype: '<class 'float'>', default: '0.0', info: 'Balance of channel 1:\n	RGB: Red\n	HSV: Hue\n	LAB: Lightness\n	YCrCb: Luma', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: color balance)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'balance_2', datatype: '<class 'float'>', default: '0.0', info: 'Balance of channel 2:\n	RGB: Green\n	HSV: Saturation\n	LAB: Green > Magenta\n	YCrCb: Distance of red from Luma', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: color balance)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'balance_3', datatype: '<class 'float'>', default: '0.0', info: 'Balance of channel 3:\n	RGB: Blue\n	HSV: Intensity\n	LAB: Blue > Yellow\n	YCrCb: Distance of blue from Luma', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: color balance)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'contrast', datatype: '<class 'float'>', default: '0.0', info: 'Amount of contrast applied.', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: brightness contrast)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'brightness', datatype: '<class 'float'>', default: '0.0', info: 'Amount of brighness applied.', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: brightness contrast)
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: color.manual_balance
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: match_hist_defaults.py, module_path: plugins.convert.color, plugin_type: color
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.color.match_hist_defaults
04/29/2020 12:09:07 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'color.match_hist', info: 'Options for matching the histograms between the source and destination faces')
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.match_hist', title: 'threshold', datatype: '<class 'float'>', default: '99.0', info: 'Adjust the threshold for histogram matching. Can reduce extreme colors leaking in by filtering out colors at the extreme ends of the histogram spectrum.', rounding: '1', min_max: (90.0, 100.0), choices: [], gui_radio: False, fixed: True, group: None)
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: color.match_hist
04/29/2020 12:09:07 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'mask']
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: box_blend_defaults.py, module_path: plugins.convert.mask, plugin_type: mask
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.mask.box_blend_defaults
04/29/2020 12:09:07 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'mask.box_blend', info: 'Options for blending the edges of the swapped box with the background image')
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'type', datatype: '<class 'str'>', default: 'gaussian', info: 'The type of blending to use:\n	 gaussian: Blend with Gaussian filter. Slower, but often better than Normalized\n	 normalized: Blend with Normalized box filter. Faster than Gaussian\n	 none: Don't perform blending', rounding: 'None', min_max: None, choices: ['gaussian', 'normalized', 'none'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'distance', datatype: '<class 'float'>', default: '11.0', info: 'The distance from the edges of the swap box to start blending.\nThe distance is set as percentage of the swap box size to give the number of pixels from the edge of the box. Eg: For a swap area of 256px and a percentage of 4%, blending would commence 10 pixels from the edge.\nHigher percentages start the blending from closer to the center of the face, so will reveal more of the source face.', rounding: '1', min_max: (0.1, 25.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'radius', datatype: '<class 'float'>', default: '5.0', info: 'Radius dictates how much blending should occur, or more specifically, how far the blending will spread away from the 'distance' parameter.\nThis figure is set as a percentage of the swap box size to give the radius in pixels. Eg: For a swap area of 256px and a percentage of 5%, the radius would be 13 pixels\nNB: Higher percentage means more blending, but too high may reveal more of the source face, or lead to hard lines at the border.', rounding: '1', min_max: (0.1, 25.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'passes', datatype: '<class 'int'>', default: '1', info: 'The number of passes to perform. Additional passes of the blending algorithm can improve smoothing at a time cost. This is more useful for 'box' type blending.\nAdditional passes have exponentially less effect so it's not worth setting this too high.', rounding: '1', min_max: (1, 8), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: mask.box_blend
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: mask_blend_defaults.py, module_path: plugins.convert.mask, plugin_type: mask
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.mask.mask_blend_defaults
04/29/2020 12:09:07 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'mask.mask_blend', info: 'Options for blending the edges between the mask and the background image')
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'type', datatype: '<class 'str'>', default: 'normalized', info: 'The type of blending to use:\n	 gaussian: Blend with Gaussian filter. Slower, but often better than Normalized\n	 normalized: Blend with Normalized box filter. Faster than Gaussian\n	 none: Don't perform blending', rounding: 'None', min_max: None, choices: ['gaussian', 'normalized', 'none'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'kernel_size', datatype: '<class 'int'>', default: '3', info: 'The kernel size dictates how much blending should occur.\nThe size is the diameter of the kernel in pixels (calculated from a 128px mask).  This value should be odd, if an even number is passed in then it will be rounded to the next odd number. Higher sizes means more blending.', rounding: '1', min_max: (1, 9), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'passes', datatype: '<class 'int'>', default: '4', info: 'The number of passes to perform. Additional passes of the blending algorithm can improve smoothing at a time cost. This is more useful for 'box' type blending.\nAdditional passes have exponentially less effect so it's not worth setting this too high.', rounding: '1', min_max: (1, 8), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'threshold', datatype: '<class 'int'>', default: '4', info: 'Sets pixels that are near white to white and near black to black. Set to 0 for off.', rounding: '1', min_max: (0, 50), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'erosion', datatype: '<class 'float'>', default: '0.0', info: 'Erosion kernel size as a percentage of the mask radius area.\nPositive values apply erosion which reduces the size of the swapped area.\nNegative values apply dilation which increases the swapped area.', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: mask.mask_blend
04/29/2020 12:09:07 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'scaling']
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: sharpen_defaults.py, module_path: plugins.convert.scaling, plugin_type: scaling
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.scaling.sharpen_defaults
04/29/2020 12:09:07 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'scaling.sharpen', info: 'Options for sharpening the face after placement')
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'method', datatype: '<class 'str'>', default: 'unsharp_mask', info: 'The type of sharpening to use:\n	 box: Fastest, but weakest method. Uses a box filter to assess edges.\n	 gaussian: Slower, but better than box. Uses a gaussian filter to assess edges.\n	 unsharp-mask: Slowest, but most tweakable. Uses the unsharp-mask method to assess edges.', rounding: 'None', min_max: None, choices: ['box', 'gaussian', 'unsharp_mask'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'amount', datatype: '<class 'int'>', default: '150', info: 'Percentage that controls the magnitude of each overshoot (how much darker and how much lighter the edge borders become).\nThis can also be thought of as how much contrast is added at the edges. It does not affect the width of the edge rims.', rounding: '1', min_max: (100, 500), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'radius', datatype: '<class 'float'>', default: '0.3', info: 'Affects the size of the edges to be enhanced or how wide the edge rims become, so a smaller radius enhances smaller-scale detail.\nRadius is set as a percentage of the final frame width and rounded to the nearest pixel. E.g for a 1280 width frame, a 0.6 percenatage will give a radius of 8px.\nHigher radius values can cause halos at the edges, a detectable faint light rim around objects. Fine detail needs a smaller radius. \nRadius and amount interact; reducing one allows more of the other.', rounding: '1', min_max: (0.1, 5.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'threshold', datatype: '<class 'float'>', default: '5.0', info: '[unsharp_mask only] Controls the minimal brightness change that will be sharpened or how far apart adjacent tonal values have to be before the filter does anything.\nThis lack of action is important to prevent smooth areas from becoming speckled. The threshold setting can be used to sharpen more pronounced edges, while leaving subtler edges untouched. \nLow values should sharpen more because fewer areas are excluded. \nHigher threshold values exclude areas of lower contrast.', rounding: '1', min_max: (1.0, 10.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: scaling.sharpen
04/29/2020 12:09:07 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'writer']
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: ffmpeg_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.ffmpeg_defaults
04/29/2020 12:09:07 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.ffmpeg', info: 'Options for encoding converted frames to video.')
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'container', datatype: '<class 'str'>', default: 'mp4', info: 'Video container to use.', rounding: 'None', min_max: None, choices: ['avi', 'flv', 'mkv', 'mov', 'mp4', 'mpeg', 'webm'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'codec', datatype: '<class 'str'>', default: 'libx264', info: 'Video codec to use:\n	 libx264: H.264. A widely supported and commonly used codec.\n	 libx265: H.265 / HEVC video encoder application library.', rounding: 'None', min_max: None, choices: ['libx264', 'libx265'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'crf', datatype: '<class 'int'>', default: '23', info: 'Constant Rate Factor:  0 is lossless and 51 is worst quality possible. A lower value generally leads to higher quality, and a subjectively sane range is 17-28. Consider 17 or 18 to be visually lossless or nearly so; it should look the same or nearly the same as the input but it isn't technically lossless.\nThe range is exponential, so increasing the CRF value +6 results in roughly half the bitrate / file size, while -6 leads to roughly twice the bitrate.', rounding: '1', min_max: (0, 51), choices: [], gui_radio: False, fixed: True, group: quality)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'preset', datatype: '<class 'str'>', default: 'medium', info: 'A preset is a collection of options that will provide a certain encoding speed to compression ratio.\nA slower preset will provide better compression (compression is quality per filesize).\nUse the slowest preset that you have patience for.', rounding: 'None', min_max: None, choices: ['ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow'], gui_radio: True, fixed: True, group: quality)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'tune', datatype: '<class 'str'>', default: 'none', info: 'Change settings based upon the specifics of your input:\n	 none: Don't perform any additional tuning.\n	 film: [H.264 only] Use for high quality movie content; lowers deblocking.\n	 animation: [H.264 only] Good for cartoons; uses higher deblocking and more reference frames.\n	 grain: Preserves the grain structure in old, grainy film material.\n	 stillimage: [H.264 only] Good for slideshow-like content.\n	 fastdecode: Allows faster decoding by disabling certain filters.\n	 zerolatency: Good for fast encoding and low-latency streaming.', rounding: 'None', min_max: None, choices: ['none', 'film', 'animation', 'grain', 'stillimage', 'fastdecode', 'zerolatency'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'profile', datatype: '<class 'str'>', default: 'auto', info: '[H.264 Only] Limit the output to a specific H.264 profile. Don't change this unless your target device only supports a certain profile.', rounding: 'None', min_max: None, choices: ['auto', 'baseline', 'main', 'high', 'high10', 'high422', 'high444'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'level', datatype: '<class 'str'>', default: 'auto', info: '[H.264 Only] Set the encoder level, Don't change this unless your target device only supports a certain level.', rounding: 'None', min_max: None, choices: ['auto', '1', '1b', '1.1', '1.2', '1.3', '2', '2.1', '2.2', '3', '3.1', '3.2', '4', '4.1', '4.2', '5', '5.1', '5.2', '6', '6.1', '6.2'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.ffmpeg
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: gif_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.gif_defaults
04/29/2020 12:09:07 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.gif', info: 'Options for outputting converted frames to an animated gif.')
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'fps', datatype: '<class 'int'>', default: '25', info: 'Frames per Second.', rounding: '1', min_max: (1, 60), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'loop', datatype: '<class 'int'>', default: '0', info: 'The number of iterations. Set to 0 to loop indefinitely.', rounding: '1', min_max: (0, 100), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'palettesize', datatype: '<class 'str'>', default: '256', info: 'The number of colors to quantize the image to. Is rounded to the nearest power of two.', rounding: 'None', min_max: None, choices: ['2', '4', '8', '16', '32', '64', '128', '256'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'subrectangles', datatype: '<class 'bool'>', default: 'False', info: 'If True, will try and optimize the GIF by storing only the rectangular parts of each frame that change with respect to the previous.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.gif
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: opencv_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.opencv_defaults
04/29/2020 12:09:07 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.opencv', info: 'Options for outputting converted frames to a series of images using OpenCV\nOpenCV can be faster than other image writers, but lacks some configuration options and formats.')
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'format', datatype: '<class 'str'>', default: 'png', info: 'Image format to use:\n	 bmp: Windows bitmap\n	 jpg: JPEG format\n	 jp2: JPEG 2000 format\n	 png: Portable Network Graphics\n	 ppm: Portable Pixmap Format', rounding: 'None', min_max: None, choices: ['bmp', 'jpg', 'jp2', 'png', 'ppm'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'draw_transparent', datatype: '<class 'bool'>', default: 'False', info: 'Place the swapped face on a transparent layer rather than the original frame.\nNB: This is only compatible with images saved in png format. If an incompatible format is selected then the image will be saved as a png.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'jpg_quality', datatype: '<class 'int'>', default: '75', info: '[jpg only] Set the jpg quality. 1 is worst 95 is best. Higher quality leads to larger file sizes.', rounding: '1', min_max: (1, 95), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'png_compress_level', datatype: '<class 'int'>', default: '3', info: '[png only] ZLIB compression level, 1 gives best speed, 9 gives best compression, 0 gives no compression at all.', rounding: '1', min_max: (0, 9), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.opencv
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: pillow_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.pillow_defaults
04/29/2020 12:09:07 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.pillow', info: 'Options for outputting converted frames to a series of images using Pillow\nPillow is more feature rich than OpenCV but can be slower.')
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'format', datatype: '<class 'str'>', default: 'png', info: 'Image format to use:\n	 bmp: Windows bitmap\n	 gif: Graphics Interchange Format (NB: Not animated)\n	 jpg: JPEG format\n	 jp2: JPEG 2000 format\n	 png: Portable Network Graphics\n	 ppm: Portable Pixmap Format\n	 tif: Tag Image File Format', rounding: 'None', min_max: None, choices: ['bmp', 'gif', 'jpg', 'jp2', 'png', 'ppm', 'tif'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'draw_transparent', datatype: '<class 'bool'>', default: 'False', info: 'Place the swapped face on a transparent layer rather than the original frame.\nNB: This is only compatible with images saved in png or tif format. If an incompatible format is selected then the image will be saved as a png.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'optimize', datatype: '<class 'bool'>', default: 'False', info: '[gif, jpg and png only] If enabled, indicates that the encoder should make an extra pass over the image in order to select optimal encoder settings.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'gif_interlace', datatype: '<class 'bool'>', default: 'True', info: '[gif only] Set whether to save the gif as interlaced or not.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'jpg_quality', datatype: '<class 'int'>', default: '75', info: '[jpg only] Set the jpg quality. 1 is worst 95 is best. Higher quality leads to larger file sizes.', rounding: '1', min_max: (1, 95), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'png_compress_level', datatype: '<class 'int'>', default: '3', info: '[png only] ZLIB compression level, 1 gives best speed, 9 gives best compression, 0 gives no compression at all. When optimize option is set to True this has no effect (it is set to 9 regardless of a value passed).', rounding: '1', min_max: (0, 9), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:07 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'tif_compression', datatype: '<class 'str'>', default: 'tiff_deflate', info: '[tif only] The desired compression method for the file.', rounding: 'None', min_max: None, choices: ['none', 'tiff_ccitt', 'group3', 'group4', 'tiff_jpeg', 'tiff_adobe_deflate', 'tiff_thunderscan', 'tiff_deflate', 'tiff_sgilog', 'tiff_sgilog24', 'tiff_raw_16'], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.pillow
04/29/2020 12:09:07 MainProcess     MainThread      config          handle_config             DEBUG    Handling config
04/29/2020 12:09:07 MainProcess     MainThread      config          check_exists              DEBUG    Config file exists: 'D:\Testing\faceswap\config\convert.ini'
04/29/2020 12:09:07 MainProcess     MainThread      config          load_config               VERBOSE  Loading config: 'D:\Testing\faceswap\config\convert.ini'
04/29/2020 12:09:07 MainProcess     MainThread      config          validate_config           DEBUG    Validating config
04/29/2020 12:09:07 MainProcess     MainThread      config          check_config_change       DEBUG    Default config has not changed
04/29/2020 12:09:07 MainProcess     MainThread      config          check_config_choices      DEBUG    Checking config choices
04/29/2020 12:09:07 MainProcess     MainThread      config          check_config_choices      DEBUG    Checked config choices
04/29/2020 12:09:07 MainProcess     MainThread      config          validate_config           DEBUG    Validated config
04/29/2020 12:09:07 MainProcess     MainThread      config          handle_config             DEBUG    Handled config
04/29/2020 12:09:07 MainProcess     MainThread      config          __init__                  DEBUG    Initialized: Config
04/29/2020 12:09:07 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'mask.box_blend', option: 'type')
04/29/2020 12:09:07 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'str'>, value: gaussian)
04/29/2020 12:09:07 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'mask.box_blend', option: 'distance')
04/29/2020 12:09:07 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'float'>, value: 11.0)
04/29/2020 12:09:07 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'mask.box_blend', option: 'radius')
04/29/2020 12:09:07 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'float'>, value: 5.0)
04/29/2020 12:09:07 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'mask.box_blend', option: 'passes')
04/29/2020 12:09:07 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'int'>, value: 1)
04/29/2020 12:09:07 MainProcess     MainThread      _base           _set_config               DEBUG    Config: {'type': 'gaussian', 'distance': 11.0, 'radius': 5.0, 'passes': 1}
04/29/2020 12:09:07 MainProcess     MainThread      _base           __init__                  DEBUG    config: {'type': 'gaussian', 'distance': 11.0, 'radius': 5.0, 'passes': 1}
04/29/2020 12:09:07 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized Mask
04/29/2020 12:09:07 MainProcess     MainThread      box_blend       _get_mask                 DEBUG    Building box mask
04/29/2020 12:09:07 MainProcess     MainThread      faces_detect    __init__                  TRACE    Initializing BlurMask: (blur_type: 'gaussian', mask_shape: (64, 64), kernel: 5.0, is_ratio: True, passes: 1)
04/29/2020 12:09:07 MainProcess     MainThread      faces_detect    _get_kernel_size          TRACE    kernel_size: 7
04/29/2020 12:09:07 MainProcess     MainThread      faces_detect    _get_kernel_tuple         TRACE    (7, 7)
04/29/2020 12:09:07 MainProcess     MainThread      faces_detect    __init__                  TRACE    Initialized BlurMask
04/29/2020 12:09:07 MainProcess     MainThread      faces_detect    _get_kwargs               TRACE    BlurMask kwargs: {'ksize': (7, 7), 'sigmaX': 0}
04/29/2020 12:09:07 MainProcess     MainThread      faces_detect    blurred                   TRACE    Pass: 1, kernel_size: (7, 7)
04/29/2020 12:09:07 MainProcess     MainThread      faces_detect    _get_kernel_tuple         TRACE    (7, 7)
04/29/2020 12:09:07 MainProcess     MainThread      faces_detect    blurred                   TRACE    Returning blurred mask. Shape: (64, 64, 1)
04/29/2020 12:09:07 MainProcess     MainThread      box_blend       _get_mask                 DEBUG    Built box mask. Shape: (64, 64, 1)
04/29/2020 12:09:07 MainProcess     MainThread      plugin_loader   _import                   INFO     Loading Mask from Mask_Blend plugin...
04/29/2020 12:09:07 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing Mask: (arguments: 'none', output_size: 64, configfile: None, config: None)
04/29/2020 12:09:07 MainProcess     MainThread      config          __init__                  DEBUG    Initializing: Config
04/29/2020 12:09:07 MainProcess     MainThread      config          get_config_file           DEBUG    Config File location: 'D:\Testing\faceswap\config\convert.ini'
04/29/2020 12:09:07 MainProcess     MainThread      _config         set_defaults              DEBUG    Setting defaults
04/29/2020 12:09:07 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'color']
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: color_transfer_defaults.py, module_path: plugins.convert.color, plugin_type: color
04/29/2020 12:09:07 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.color.color_transfer_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'color.color_transfer', info: 'Options for transfering the color distribution from the source to the target image using the mean and standard deviations of the L*a*b* color space.\nThis implementation is (loosely) based on the 'Color Transfer between Images' paper by Reinhard et al., 2001. matching the histograms between the source and destination faces.')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.color_transfer', title: 'clip', datatype: '<class 'bool'>', default: 'True', info: 'Should components of L*a*b* image be scaled by np.clip before converting back to BGR color space?\nIf False then components will be min-max scaled appropriately.\nClipping will keep target image brightness truer to the input.\nScaling will adjust image brightness to avoid washed out portions in the resulting color transfer that can be caused by clipping.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: method)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.color_transfer', title: 'preserve_paper', datatype: '<class 'bool'>', default: 'True', info: 'Should color transfer strictly follow methodology layed out in original paper?\nThe method does not always produce aesthetically pleasing results.\nIf False then L*a*b* components will be scaled using the reciprocal of the scaling factor proposed in the paper. This method seems to produce more consistently aesthetically pleasing results.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: method)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: color.color_transfer
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: manual_balance_defaults.py, module_path: plugins.convert.color, plugin_type: color
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.color.manual_balance_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'color.manual_balance', info: 'Options for manually altering the balance of colors of the swapped face')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'colorspace', datatype: '<class 'str'>', default: 'HSV', info: 'The colorspace to use for adjustment: The three adjustment sliders will effect the image differently depending on which colorspace is selected:\n	 RGB: Red, Green, Blue. An additive colorspace where colors are obtained by a linear combination of Red, Green, and Blue values. The three channels are correlated by the amount of light hitting the surface. In RGB color space the color information is separated into three channels but the same three channels also encode brightness information.\n	 HSV: Hue, Saturation, Value. Hue - Dominant wavelength. Saturation - Purity / shades of color. Value - Intensity. Best thing is that it uses only one channel to describe color (H), making it very intuitive to specify color.\n	 LAB: Lightness, A, B. Lightness - Intensity. A - Color range from green to magenta. B - Color range from blue to yellow. The L channel is independent of color information and encodes brightness only. The other two channels encode color.\n	 YCrCb: Y - Luminance or Luma component obtained from RGB after gamma correction. Cr - how far is the red component from Luma. Cb - how far is the blue component from Luma. Separates the luminance and chrominance components into different channels.', rounding: 'None', min_max: None, choices: ['RGB', 'HSV', 'LAB', 'YCrCb'], gui_radio: True, fixed: True, group: color balance)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'balance_1', datatype: '<class 'float'>', default: '0.0', info: 'Balance of channel 1:\n	RGB: Red\n	HSV: Hue\n	LAB: Lightness\n	YCrCb: Luma', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: color balance)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'balance_2', datatype: '<class 'float'>', default: '0.0', info: 'Balance of channel 2:\n	RGB: Green\n	HSV: Saturation\n	LAB: Green > Magenta\n	YCrCb: Distance of red from Luma', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: color balance)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'balance_3', datatype: '<class 'float'>', default: '0.0', info: 'Balance of channel 3:\n	RGB: Blue\n	HSV: Intensity\n	LAB: Blue > Yellow\n	YCrCb: Distance of blue from Luma', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: color balance)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'contrast', datatype: '<class 'float'>', default: '0.0', info: 'Amount of contrast applied.', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: brightness contrast)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'brightness', datatype: '<class 'float'>', default: '0.0', info: 'Amount of brighness applied.', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: brightness contrast)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: color.manual_balance
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: match_hist_defaults.py, module_path: plugins.convert.color, plugin_type: color
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.color.match_hist_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'color.match_hist', info: 'Options for matching the histograms between the source and destination faces')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.match_hist', title: 'threshold', datatype: '<class 'float'>', default: '99.0', info: 'Adjust the threshold for histogram matching. Can reduce extreme colors leaking in by filtering out colors at the extreme ends of the histogram spectrum.', rounding: '1', min_max: (90.0, 100.0), choices: [], gui_radio: False, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: color.match_hist
04/29/2020 12:09:08 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'mask']
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: box_blend_defaults.py, module_path: plugins.convert.mask, plugin_type: mask
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.mask.box_blend_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'mask.box_blend', info: 'Options for blending the edges of the swapped box with the background image')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'type', datatype: '<class 'str'>', default: 'gaussian', info: 'The type of blending to use:\n	 gaussian: Blend with Gaussian filter. Slower, but often better than Normalized\n	 normalized: Blend with Normalized box filter. Faster than Gaussian\n	 none: Don't perform blending', rounding: 'None', min_max: None, choices: ['gaussian', 'normalized', 'none'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'distance', datatype: '<class 'float'>', default: '11.0', info: 'The distance from the edges of the swap box to start blending.\nThe distance is set as percentage of the swap box size to give the number of pixels from the edge of the box. Eg: For a swap area of 256px and a percentage of 4%, blending would commence 10 pixels from the edge.\nHigher percentages start the blending from closer to the center of the face, so will reveal more of the source face.', rounding: '1', min_max: (0.1, 25.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'radius', datatype: '<class 'float'>', default: '5.0', info: 'Radius dictates how much blending should occur, or more specifically, how far the blending will spread away from the 'distance' parameter.\nThis figure is set as a percentage of the swap box size to give the radius in pixels. Eg: For a swap area of 256px and a percentage of 5%, the radius would be 13 pixels\nNB: Higher percentage means more blending, but too high may reveal more of the source face, or lead to hard lines at the border.', rounding: '1', min_max: (0.1, 25.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'passes', datatype: '<class 'int'>', default: '1', info: 'The number of passes to perform. Additional passes of the blending algorithm can improve smoothing at a time cost. This is more useful for 'box' type blending.\nAdditional passes have exponentially less effect so it's not worth setting this too high.', rounding: '1', min_max: (1, 8), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: mask.box_blend
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: mask_blend_defaults.py, module_path: plugins.convert.mask, plugin_type: mask
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.mask.mask_blend_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'mask.mask_blend', info: 'Options for blending the edges between the mask and the background image')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'type', datatype: '<class 'str'>', default: 'normalized', info: 'The type of blending to use:\n	 gaussian: Blend with Gaussian filter. Slower, but often better than Normalized\n	 normalized: Blend with Normalized box filter. Faster than Gaussian\n	 none: Don't perform blending', rounding: 'None', min_max: None, choices: ['gaussian', 'normalized', 'none'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'kernel_size', datatype: '<class 'int'>', default: '3', info: 'The kernel size dictates how much blending should occur.\nThe size is the diameter of the kernel in pixels (calculated from a 128px mask).  This value should be odd, if an even number is passed in then it will be rounded to the next odd number. Higher sizes means more blending.', rounding: '1', min_max: (1, 9), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'passes', datatype: '<class 'int'>', default: '4', info: 'The number of passes to perform. Additional passes of the blending algorithm can improve smoothing at a time cost. This is more useful for 'box' type blending.\nAdditional passes have exponentially less effect so it's not worth setting this too high.', rounding: '1', min_max: (1, 8), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'threshold', datatype: '<class 'int'>', default: '4', info: 'Sets pixels that are near white to white and near black to black. Set to 0 for off.', rounding: '1', min_max: (0, 50), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'erosion', datatype: '<class 'float'>', default: '0.0', info: 'Erosion kernel size as a percentage of the mask radius area.\nPositive values apply erosion which reduces the size of the swapped area.\nNegative values apply dilation which increases the swapped area.', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: mask.mask_blend
04/29/2020 12:09:08 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'scaling']
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: sharpen_defaults.py, module_path: plugins.convert.scaling, plugin_type: scaling
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.scaling.sharpen_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'scaling.sharpen', info: 'Options for sharpening the face after placement')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'method', datatype: '<class 'str'>', default: 'unsharp_mask', info: 'The type of sharpening to use:\n	 box: Fastest, but weakest method. Uses a box filter to assess edges.\n	 gaussian: Slower, but better than box. Uses a gaussian filter to assess edges.\n	 unsharp-mask: Slowest, but most tweakable. Uses the unsharp-mask method to assess edges.', rounding: 'None', min_max: None, choices: ['box', 'gaussian', 'unsharp_mask'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'amount', datatype: '<class 'int'>', default: '150', info: 'Percentage that controls the magnitude of each overshoot (how much darker and how much lighter the edge borders become).\nThis can also be thought of as how much contrast is added at the edges. It does not affect the width of the edge rims.', rounding: '1', min_max: (100, 500), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'radius', datatype: '<class 'float'>', default: '0.3', info: 'Affects the size of the edges to be enhanced or how wide the edge rims become, so a smaller radius enhances smaller-scale detail.\nRadius is set as a percentage of the final frame width and rounded to the nearest pixel. E.g for a 1280 width frame, a 0.6 percenatage will give a radius of 8px.\nHigher radius values can cause halos at the edges, a detectable faint light rim around objects. Fine detail needs a smaller radius. \nRadius and amount interact; reducing one allows more of the other.', rounding: '1', min_max: (0.1, 5.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'threshold', datatype: '<class 'float'>', default: '5.0', info: '[unsharp_mask only] Controls the minimal brightness change that will be sharpened or how far apart adjacent tonal values have to be before the filter does anything.\nThis lack of action is important to prevent smooth areas from becoming speckled. The threshold setting can be used to sharpen more pronounced edges, while leaving subtler edges untouched. \nLow values should sharpen more because fewer areas are excluded. \nHigher threshold values exclude areas of lower contrast.', rounding: '1', min_max: (1.0, 10.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: scaling.sharpen
04/29/2020 12:09:08 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'writer']
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: ffmpeg_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.ffmpeg_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.ffmpeg', info: 'Options for encoding converted frames to video.')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'container', datatype: '<class 'str'>', default: 'mp4', info: 'Video container to use.', rounding: 'None', min_max: None, choices: ['avi', 'flv', 'mkv', 'mov', 'mp4', 'mpeg', 'webm'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'codec', datatype: '<class 'str'>', default: 'libx264', info: 'Video codec to use:\n	 libx264: H.264. A widely supported and commonly used codec.\n	 libx265: H.265 / HEVC video encoder application library.', rounding: 'None', min_max: None, choices: ['libx264', 'libx265'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'crf', datatype: '<class 'int'>', default: '23', info: 'Constant Rate Factor:  0 is lossless and 51 is worst quality possible. A lower value generally leads to higher quality, and a subjectively sane range is 17-28. Consider 17 or 18 to be visually lossless or nearly so; it should look the same or nearly the same as the input but it isn't technically lossless.\nThe range is exponential, so increasing the CRF value +6 results in roughly half the bitrate / file size, while -6 leads to roughly twice the bitrate.', rounding: '1', min_max: (0, 51), choices: [], gui_radio: False, fixed: True, group: quality)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'preset', datatype: '<class 'str'>', default: 'medium', info: 'A preset is a collection of options that will provide a certain encoding speed to compression ratio.\nA slower preset will provide better compression (compression is quality per filesize).\nUse the slowest preset that you have patience for.', rounding: 'None', min_max: None, choices: ['ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow'], gui_radio: True, fixed: True, group: quality)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'tune', datatype: '<class 'str'>', default: 'none', info: 'Change settings based upon the specifics of your input:\n	 none: Don't perform any additional tuning.\n	 film: [H.264 only] Use for high quality movie content; lowers deblocking.\n	 animation: [H.264 only] Good for cartoons; uses higher deblocking and more reference frames.\n	 grain: Preserves the grain structure in old, grainy film material.\n	 stillimage: [H.264 only] Good for slideshow-like content.\n	 fastdecode: Allows faster decoding by disabling certain filters.\n	 zerolatency: Good for fast encoding and low-latency streaming.', rounding: 'None', min_max: None, choices: ['none', 'film', 'animation', 'grain', 'stillimage', 'fastdecode', 'zerolatency'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'profile', datatype: '<class 'str'>', default: 'auto', info: '[H.264 Only] Limit the output to a specific H.264 profile. Don't change this unless your target device only supports a certain profile.', rounding: 'None', min_max: None, choices: ['auto', 'baseline', 'main', 'high', 'high10', 'high422', 'high444'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'level', datatype: '<class 'str'>', default: 'auto', info: '[H.264 Only] Set the encoder level, Don't change this unless your target device only supports a certain level.', rounding: 'None', min_max: None, choices: ['auto', '1', '1b', '1.1', '1.2', '1.3', '2', '2.1', '2.2', '3', '3.1', '3.2', '4', '4.1', '4.2', '5', '5.1', '5.2', '6', '6.1', '6.2'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.ffmpeg
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: gif_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.gif_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.gif', info: 'Options for outputting converted frames to an animated gif.')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'fps', datatype: '<class 'int'>', default: '25', info: 'Frames per Second.', rounding: '1', min_max: (1, 60), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'loop', datatype: '<class 'int'>', default: '0', info: 'The number of iterations. Set to 0 to loop indefinitely.', rounding: '1', min_max: (0, 100), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'palettesize', datatype: '<class 'str'>', default: '256', info: 'The number of colors to quantize the image to. Is rounded to the nearest power of two.', rounding: 'None', min_max: None, choices: ['2', '4', '8', '16', '32', '64', '128', '256'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'subrectangles', datatype: '<class 'bool'>', default: 'False', info: 'If True, will try and optimize the GIF by storing only the rectangular parts of each frame that change with respect to the previous.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.gif
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: opencv_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.opencv_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.opencv', info: 'Options for outputting converted frames to a series of images using OpenCV\nOpenCV can be faster than other image writers, but lacks some configuration options and formats.')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'format', datatype: '<class 'str'>', default: 'png', info: 'Image format to use:\n	 bmp: Windows bitmap\n	 jpg: JPEG format\n	 jp2: JPEG 2000 format\n	 png: Portable Network Graphics\n	 ppm: Portable Pixmap Format', rounding: 'None', min_max: None, choices: ['bmp', 'jpg', 'jp2', 'png', 'ppm'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'draw_transparent', datatype: '<class 'bool'>', default: 'False', info: 'Place the swapped face on a transparent layer rather than the original frame.\nNB: This is only compatible with images saved in png format. If an incompatible format is selected then the image will be saved as a png.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'jpg_quality', datatype: '<class 'int'>', default: '75', info: '[jpg only] Set the jpg quality. 1 is worst 95 is best. Higher quality leads to larger file sizes.', rounding: '1', min_max: (1, 95), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'png_compress_level', datatype: '<class 'int'>', default: '3', info: '[png only] ZLIB compression level, 1 gives best speed, 9 gives best compression, 0 gives no compression at all.', rounding: '1', min_max: (0, 9), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.opencv
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: pillow_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.pillow_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.pillow', info: 'Options for outputting converted frames to a series of images using Pillow\nPillow is more feature rich than OpenCV but can be slower.')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'format', datatype: '<class 'str'>', default: 'png', info: 'Image format to use:\n	 bmp: Windows bitmap\n	 gif: Graphics Interchange Format (NB: Not animated)\n	 jpg: JPEG format\n	 jp2: JPEG 2000 format\n	 png: Portable Network Graphics\n	 ppm: Portable Pixmap Format\n	 tif: Tag Image File Format', rounding: 'None', min_max: None, choices: ['bmp', 'gif', 'jpg', 'jp2', 'png', 'ppm', 'tif'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'draw_transparent', datatype: '<class 'bool'>', default: 'False', info: 'Place the swapped face on a transparent layer rather than the original frame.\nNB: This is only compatible with images saved in png or tif format. If an incompatible format is selected then the image will be saved as a png.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'optimize', datatype: '<class 'bool'>', default: 'False', info: '[gif, jpg and png only] If enabled, indicates that the encoder should make an extra pass over the image in order to select optimal encoder settings.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'gif_interlace', datatype: '<class 'bool'>', default: 'True', info: '[gif only] Set whether to save the gif as interlaced or not.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'jpg_quality', datatype: '<class 'int'>', default: '75', info: '[jpg only] Set the jpg quality. 1 is worst 95 is best. Higher quality leads to larger file sizes.', rounding: '1', min_max: (1, 95), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'png_compress_level', datatype: '<class 'int'>', default: '3', info: '[png only] ZLIB compression level, 1 gives best speed, 9 gives best compression, 0 gives no compression at all. When optimize option is set to True this has no effect (it is set to 9 regardless of a value passed).', rounding: '1', min_max: (0, 9), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'tif_compression', datatype: '<class 'str'>', default: 'tiff_deflate', info: '[tif only] The desired compression method for the file.', rounding: 'None', min_max: None, choices: ['none', 'tiff_ccitt', 'group3', 'group4', 'tiff_jpeg', 'tiff_adobe_deflate', 'tiff_thunderscan', 'tiff_deflate', 'tiff_sgilog', 'tiff_sgilog24', 'tiff_raw_16'], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.pillow
04/29/2020 12:09:08 MainProcess     MainThread      config          handle_config             DEBUG    Handling config
04/29/2020 12:09:08 MainProcess     MainThread      config          check_exists              DEBUG    Config file exists: 'D:\Testing\faceswap\config\convert.ini'
04/29/2020 12:09:08 MainProcess     MainThread      config          load_config               VERBOSE  Loading config: 'D:\Testing\faceswap\config\convert.ini'
04/29/2020 12:09:08 MainProcess     MainThread      config          validate_config           DEBUG    Validating config
04/29/2020 12:09:08 MainProcess     MainThread      config          check_config_change       DEBUG    Default config has not changed
04/29/2020 12:09:08 MainProcess     MainThread      config          check_config_choices      DEBUG    Checking config choices
04/29/2020 12:09:08 MainProcess     MainThread      config          check_config_choices      DEBUG    Checked config choices
04/29/2020 12:09:08 MainProcess     MainThread      config          validate_config           DEBUG    Validated config
04/29/2020 12:09:08 MainProcess     MainThread      config          handle_config             DEBUG    Handled config
04/29/2020 12:09:08 MainProcess     MainThread      config          __init__                  DEBUG    Initialized: Config
04/29/2020 12:09:08 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'mask.mask_blend', option: 'type')
04/29/2020 12:09:08 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'str'>, value: normalized)
04/29/2020 12:09:08 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'mask.mask_blend', option: 'kernel_size')
04/29/2020 12:09:08 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'int'>, value: 3)
04/29/2020 12:09:08 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'mask.mask_blend', option: 'passes')
04/29/2020 12:09:08 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'int'>, value: 4)
04/29/2020 12:09:08 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'mask.mask_blend', option: 'threshold')
04/29/2020 12:09:08 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'int'>, value: 4)
04/29/2020 12:09:08 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'mask.mask_blend', option: 'erosion')
04/29/2020 12:09:08 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'float'>, value: 0.0)
04/29/2020 12:09:08 MainProcess     MainThread      _base           _set_config               DEBUG    Config: {'type': 'normalized', 'kernel_size': 3, 'passes': 4, 'threshold': 4, 'erosion': 0.0}
04/29/2020 12:09:08 MainProcess     MainThread      _base           __init__                  DEBUG    config: {'type': 'normalized', 'kernel_size': 3, 'passes': 4, 'threshold': 4, 'erosion': 0.0}
04/29/2020 12:09:08 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized Mask
04/29/2020 12:09:08 MainProcess     MainThread      plugin_loader   _import                   INFO     Loading Color from Avg_Color plugin...
04/29/2020 12:09:08 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing Color: (configfile: None, config: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          __init__                  DEBUG    Initializing: Config
04/29/2020 12:09:08 MainProcess     MainThread      config          get_config_file           DEBUG    Config File location: 'D:\Testing\faceswap\config\convert.ini'
04/29/2020 12:09:08 MainProcess     MainThread      _config         set_defaults              DEBUG    Setting defaults
04/29/2020 12:09:08 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'color']
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: color_transfer_defaults.py, module_path: plugins.convert.color, plugin_type: color
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.color.color_transfer_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'color.color_transfer', info: 'Options for transfering the color distribution from the source to the target image using the mean and standard deviations of the L*a*b* color space.\nThis implementation is (loosely) based on the 'Color Transfer between Images' paper by Reinhard et al., 2001. matching the histograms between the source and destination faces.')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.color_transfer', title: 'clip', datatype: '<class 'bool'>', default: 'True', info: 'Should components of L*a*b* image be scaled by np.clip before converting back to BGR color space?\nIf False then components will be min-max scaled appropriately.\nClipping will keep target image brightness truer to the input.\nScaling will adjust image brightness to avoid washed out portions in the resulting color transfer that can be caused by clipping.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: method)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.color_transfer', title: 'preserve_paper', datatype: '<class 'bool'>', default: 'True', info: 'Should color transfer strictly follow methodology layed out in original paper?\nThe method does not always produce aesthetically pleasing results.\nIf False then L*a*b* components will be scaled using the reciprocal of the scaling factor proposed in the paper. This method seems to produce more consistently aesthetically pleasing results.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: method)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: color.color_transfer
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: manual_balance_defaults.py, module_path: plugins.convert.color, plugin_type: color
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.color.manual_balance_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'color.manual_balance', info: 'Options for manually altering the balance of colors of the swapped face')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'colorspace', datatype: '<class 'str'>', default: 'HSV', info: 'The colorspace to use for adjustment: The three adjustment sliders will effect the image differently depending on which colorspace is selected:\n	 RGB: Red, Green, Blue. An additive colorspace where colors are obtained by a linear combination of Red, Green, and Blue values. The three channels are correlated by the amount of light hitting the surface. In RGB color space the color information is separated into three channels but the same three channels also encode brightness information.\n	 HSV: Hue, Saturation, Value. Hue - Dominant wavelength. Saturation - Purity / shades of color. Value - Intensity. Best thing is that it uses only one channel to describe color (H), making it very intuitive to specify color.\n	 LAB: Lightness, A, B. Lightness - Intensity. A - Color range from green to magenta. B - Color range from blue to yellow. The L channel is independent of color information and encodes brightness only. The other two channels encode color.\n	 YCrCb: Y - Luminance or Luma component obtained from RGB after gamma correction. Cr - how far is the red component from Luma. Cb - how far is the blue component from Luma. Separates the luminance and chrominance components into different channels.', rounding: 'None', min_max: None, choices: ['RGB', 'HSV', 'LAB', 'YCrCb'], gui_radio: True, fixed: True, group: color balance)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'balance_1', datatype: '<class 'float'>', default: '0.0', info: 'Balance of channel 1:\n	RGB: Red\n	HSV: Hue\n	LAB: Lightness\n	YCrCb: Luma', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: color balance)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'balance_2', datatype: '<class 'float'>', default: '0.0', info: 'Balance of channel 2:\n	RGB: Green\n	HSV: Saturation\n	LAB: Green > Magenta\n	YCrCb: Distance of red from Luma', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: color balance)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'balance_3', datatype: '<class 'float'>', default: '0.0', info: 'Balance of channel 3:\n	RGB: Blue\n	HSV: Intensity\n	LAB: Blue > Yellow\n	YCrCb: Distance of blue from Luma', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: color balance)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'contrast', datatype: '<class 'float'>', default: '0.0', info: 'Amount of contrast applied.', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: brightness contrast)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.manual_balance', title: 'brightness', datatype: '<class 'float'>', default: '0.0', info: 'Amount of brighness applied.', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: brightness contrast)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: color.manual_balance
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: match_hist_defaults.py, module_path: plugins.convert.color, plugin_type: color
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.color.match_hist_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'color.match_hist', info: 'Options for matching the histograms between the source and destination faces')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'color.match_hist', title: 'threshold', datatype: '<class 'float'>', default: '99.0', info: 'Adjust the threshold for histogram matching. Can reduce extreme colors leaking in by filtering out colors at the extreme ends of the histogram spectrum.', rounding: '1', min_max: (90.0, 100.0), choices: [], gui_radio: False, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: color.match_hist
04/29/2020 12:09:08 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'mask']
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: box_blend_defaults.py, module_path: plugins.convert.mask, plugin_type: mask
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.mask.box_blend_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'mask.box_blend', info: 'Options for blending the edges of the swapped box with the background image')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'type', datatype: '<class 'str'>', default: 'gaussian', info: 'The type of blending to use:\n	 gaussian: Blend with Gaussian filter. Slower, but often better than Normalized\n	 normalized: Blend with Normalized box filter. Faster than Gaussian\n	 none: Don't perform blending', rounding: 'None', min_max: None, choices: ['gaussian', 'normalized', 'none'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'distance', datatype: '<class 'float'>', default: '11.0', info: 'The distance from the edges of the swap box to start blending.\nThe distance is set as percentage of the swap box size to give the number of pixels from the edge of the box. Eg: For a swap area of 256px and a percentage of 4%, blending would commence 10 pixels from the edge.\nHigher percentages start the blending from closer to the center of the face, so will reveal more of the source face.', rounding: '1', min_max: (0.1, 25.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'radius', datatype: '<class 'float'>', default: '5.0', info: 'Radius dictates how much blending should occur, or more specifically, how far the blending will spread away from the 'distance' parameter.\nThis figure is set as a percentage of the swap box size to give the radius in pixels. Eg: For a swap area of 256px and a percentage of 5%, the radius would be 13 pixels\nNB: Higher percentage means more blending, but too high may reveal more of the source face, or lead to hard lines at the border.', rounding: '1', min_max: (0.1, 25.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.box_blend', title: 'passes', datatype: '<class 'int'>', default: '1', info: 'The number of passes to perform. Additional passes of the blending algorithm can improve smoothing at a time cost. This is more useful for 'box' type blending.\nAdditional passes have exponentially less effect so it's not worth setting this too high.', rounding: '1', min_max: (1, 8), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: mask.box_blend
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: mask_blend_defaults.py, module_path: plugins.convert.mask, plugin_type: mask
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.mask.mask_blend_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'mask.mask_blend', info: 'Options for blending the edges between the mask and the background image')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'type', datatype: '<class 'str'>', default: 'normalized', info: 'The type of blending to use:\n	 gaussian: Blend with Gaussian filter. Slower, but often better than Normalized\n	 normalized: Blend with Normalized box filter. Faster than Gaussian\n	 none: Don't perform blending', rounding: 'None', min_max: None, choices: ['gaussian', 'normalized', 'none'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'kernel_size', datatype: '<class 'int'>', default: '3', info: 'The kernel size dictates how much blending should occur.\nThe size is the diameter of the kernel in pixels (calculated from a 128px mask).  This value should be odd, if an even number is passed in then it will be rounded to the next odd number. Higher sizes means more blending.', rounding: '1', min_max: (1, 9), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'passes', datatype: '<class 'int'>', default: '4', info: 'The number of passes to perform. Additional passes of the blending algorithm can improve smoothing at a time cost. This is more useful for 'box' type blending.\nAdditional passes have exponentially less effect so it's not worth setting this too high.', rounding: '1', min_max: (1, 8), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'threshold', datatype: '<class 'int'>', default: '4', info: 'Sets pixels that are near white to white and near black to black. Set to 0 for off.', rounding: '1', min_max: (0, 50), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'mask.mask_blend', title: 'erosion', datatype: '<class 'float'>', default: '0.0', info: 'Erosion kernel size as a percentage of the mask radius area.\nPositive values apply erosion which reduces the size of the swapped area.\nNegative values apply dilation which increases the swapped area.', rounding: '1', min_max: (-100.0, 100.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: mask.mask_blend
04/29/2020 12:09:08 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'scaling']
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: sharpen_defaults.py, module_path: plugins.convert.scaling, plugin_type: scaling
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.scaling.sharpen_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'scaling.sharpen', info: 'Options for sharpening the face after placement')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'method', datatype: '<class 'str'>', default: 'unsharp_mask', info: 'The type of sharpening to use:\n	 box: Fastest, but weakest method. Uses a box filter to assess edges.\n	 gaussian: Slower, but better than box. Uses a gaussian filter to assess edges.\n	 unsharp-mask: Slowest, but most tweakable. Uses the unsharp-mask method to assess edges.', rounding: 'None', min_max: None, choices: ['box', 'gaussian', 'unsharp_mask'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'amount', datatype: '<class 'int'>', default: '150', info: 'Percentage that controls the magnitude of each overshoot (how much darker and how much lighter the edge borders become).\nThis can also be thought of as how much contrast is added at the edges. It does not affect the width of the edge rims.', rounding: '1', min_max: (100, 500), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'radius', datatype: '<class 'float'>', default: '0.3', info: 'Affects the size of the edges to be enhanced or how wide the edge rims become, so a smaller radius enhances smaller-scale detail.\nRadius is set as a percentage of the final frame width and rounded to the nearest pixel. E.g for a 1280 width frame, a 0.6 percenatage will give a radius of 8px.\nHigher radius values can cause halos at the edges, a detectable faint light rim around objects. Fine detail needs a smaller radius. \nRadius and amount interact; reducing one allows more of the other.', rounding: '1', min_max: (0.1, 5.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'scaling.sharpen', title: 'threshold', datatype: '<class 'float'>', default: '5.0', info: '[unsharp_mask only] Controls the minimal brightness change that will be sharpened or how far apart adjacent tonal values have to be before the filter does anything.\nThis lack of action is important to prevent smooth areas from becoming speckled. The threshold setting can be used to sharpen more pronounced edges, while leaving subtler edges untouched. \nLow values should sharpen more because fewer areas are excluded. \nHigher threshold values exclude areas of lower contrast.', rounding: '1', min_max: (1.0, 10.0), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: scaling.sharpen
04/29/2020 12:09:08 MainProcess     MainThread      utils           full_path_split           TRACE    path: \, allparts: ['\\', 'plugins', 'convert', 'writer']
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: ffmpeg_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.ffmpeg_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.ffmpeg', info: 'Options for encoding converted frames to video.')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'container', datatype: '<class 'str'>', default: 'mp4', info: 'Video container to use.', rounding: 'None', min_max: None, choices: ['avi', 'flv', 'mkv', 'mov', 'mp4', 'mpeg', 'webm'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'codec', datatype: '<class 'str'>', default: 'libx264', info: 'Video codec to use:\n	 libx264: H.264. A widely supported and commonly used codec.\n	 libx265: H.265 / HEVC video encoder application library.', rounding: 'None', min_max: None, choices: ['libx264', 'libx265'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'crf', datatype: '<class 'int'>', default: '23', info: 'Constant Rate Factor:  0 is lossless and 51 is worst quality possible. A lower value generally leads to higher quality, and a subjectively sane range is 17-28. Consider 17 or 18 to be visually lossless or nearly so; it should look the same or nearly the same as the input but it isn't technically lossless.\nThe range is exponential, so increasing the CRF value +6 results in roughly half the bitrate / file size, while -6 leads to roughly twice the bitrate.', rounding: '1', min_max: (0, 51), choices: [], gui_radio: False, fixed: True, group: quality)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'preset', datatype: '<class 'str'>', default: 'medium', info: 'A preset is a collection of options that will provide a certain encoding speed to compression ratio.\nA slower preset will provide better compression (compression is quality per filesize).\nUse the slowest preset that you have patience for.', rounding: 'None', min_max: None, choices: ['ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow'], gui_radio: True, fixed: True, group: quality)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'tune', datatype: '<class 'str'>', default: 'none', info: 'Change settings based upon the specifics of your input:\n	 none: Don't perform any additional tuning.\n	 film: [H.264 only] Use for high quality movie content; lowers deblocking.\n	 animation: [H.264 only] Good for cartoons; uses higher deblocking and more reference frames.\n	 grain: Preserves the grain structure in old, grainy film material.\n	 stillimage: [H.264 only] Good for slideshow-like content.\n	 fastdecode: Allows faster decoding by disabling certain filters.\n	 zerolatency: Good for fast encoding and low-latency streaming.', rounding: 'None', min_max: None, choices: ['none', 'film', 'animation', 'grain', 'stillimage', 'fastdecode', 'zerolatency'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'profile', datatype: '<class 'str'>', default: 'auto', info: '[H.264 Only] Limit the output to a specific H.264 profile. Don't change this unless your target device only supports a certain profile.', rounding: 'None', min_max: None, choices: ['auto', 'baseline', 'main', 'high', 'high10', 'high422', 'high444'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'level', datatype: '<class 'str'>', default: 'auto', info: '[H.264 Only] Set the encoder level, Don't change this unless your target device only supports a certain level.', rounding: 'None', min_max: None, choices: ['auto', '1', '1b', '1.1', '1.2', '1.3', '2', '2.1', '2.2', '3', '3.1', '3.2', '4', '4.1', '4.2', '5', '5.1', '5.2', '6', '6.1', '6.2'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.ffmpeg
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: gif_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.gif_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.gif', info: 'Options for outputting converted frames to an animated gif.')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'fps', datatype: '<class 'int'>', default: '25', info: 'Frames per Second.', rounding: '1', min_max: (1, 60), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'loop', datatype: '<class 'int'>', default: '0', info: 'The number of iterations. Set to 0 to loop indefinitely.', rounding: '1', min_max: (0, 100), choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'palettesize', datatype: '<class 'str'>', default: '256', info: 'The number of colors to quantize the image to. Is rounded to the nearest power of two.', rounding: 'None', min_max: None, choices: ['2', '4', '8', '16', '32', '64', '128', '256'], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'subrectangles', datatype: '<class 'bool'>', default: 'False', info: 'If True, will try and optimize the GIF by storing only the rectangular parts of each frame that change with respect to the previous.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.gif
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: opencv_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.opencv_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.opencv', info: 'Options for outputting converted frames to a series of images using OpenCV\nOpenCV can be faster than other image writers, but lacks some configuration options and formats.')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'format', datatype: '<class 'str'>', default: 'png', info: 'Image format to use:\n	 bmp: Windows bitmap\n	 jpg: JPEG format\n	 jp2: JPEG 2000 format\n	 png: Portable Network Graphics\n	 ppm: Portable Pixmap Format', rounding: 'None', min_max: None, choices: ['bmp', 'jpg', 'jp2', 'png', 'ppm'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'draw_transparent', datatype: '<class 'bool'>', default: 'False', info: 'Place the swapped face on a transparent layer rather than the original frame.\nNB: This is only compatible with images saved in png format. If an incompatible format is selected then the image will be saved as a png.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'jpg_quality', datatype: '<class 'int'>', default: '75', info: '[jpg only] Set the jpg quality. 1 is worst 95 is best. Higher quality leads to larger file sizes.', rounding: '1', min_max: (1, 95), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'png_compress_level', datatype: '<class 'int'>', default: '3', info: '[png only] ZLIB compression level, 1 gives best speed, 9 gives best compression, 0 gives no compression at all.', rounding: '1', min_max: (0, 9), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.opencv
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: pillow_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.pillow_defaults
04/29/2020 12:09:08 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.pillow', info: 'Options for outputting converted frames to a series of images using Pillow\nPillow is more feature rich than OpenCV but can be slower.')
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'format', datatype: '<class 'str'>', default: 'png', info: 'Image format to use:\n	 bmp: Windows bitmap\n	 gif: Graphics Interchange Format (NB: Not animated)\n	 jpg: JPEG format\n	 jp2: JPEG 2000 format\n	 png: Portable Network Graphics\n	 ppm: Portable Pixmap Format\n	 tif: Tag Image File Format', rounding: 'None', min_max: None, choices: ['bmp', 'gif', 'jpg', 'jp2', 'png', 'ppm', 'tif'], gui_radio: True, fixed: True, group: None)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'draw_transparent', datatype: '<class 'bool'>', default: 'False', info: 'Place the swapped face on a transparent layer rather than the original frame.\nNB: This is only compatible with images saved in png or tif format. If an incompatible format is selected then the image will be saved as a png.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'optimize', datatype: '<class 'bool'>', default: 'False', info: '[gif, jpg and png only] If enabled, indicates that the encoder should make an extra pass over the image in order to select optimal encoder settings.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'gif_interlace', datatype: '<class 'bool'>', default: 'True', info: '[gif only] Set whether to save the gif as interlaced or not.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'jpg_quality', datatype: '<class 'int'>', default: '75', info: '[jpg only] Set the jpg quality. 1 is worst 95 is best. Higher quality leads to larger file sizes.', rounding: '1', min_max: (1, 95), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'png_compress_level', datatype: '<class 'int'>', default: '3', info: '[png only] ZLIB compression level, 1 gives best speed, 9 gives best compression, 0 gives no compression at all. When optimize option is set to True this has no effect (it is set to 9 regardless of a value passed).', rounding: '1', min_max: (0, 9), choices: [], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:08 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'tif_compression', datatype: '<class 'str'>', default: 'tiff_deflate', info: '[tif only] The desired compression method for the file.', rounding: 'None', min_max: None, choices: ['none', 'tiff_ccitt', 'group3', 'group4', 'tiff_jpeg', 'tiff_adobe_deflate', 'tiff_thunderscan', 'tiff_deflate', 'tiff_sgilog', 'tiff_sgilog24', 'tiff_raw_16'], gui_radio: False, fixed: True, group: compression)
04/29/2020 12:09:08 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.pillow
04/29/2020 12:09:08 MainProcess     MainThread      config          handle_config             DEBUG    Handling config
04/29/2020 12:09:08 MainProcess     MainThread      config          check_exists              DEBUG    Config file exists: 'D:\Testing\faceswap\config\convert.ini'
04/29/2020 12:09:08 MainProcess     MainThread      config          load_config               VERBOSE  Loading config: 'D:\Testing\faceswap\config\convert.ini'
04/29/2020 12:09:08 MainProcess     MainThread      config          validate_config           DEBUG    Validating config
04/29/2020 12:09:08 MainProcess     MainThread      config          check_config_change       DEBUG    Default config has not changed
04/29/2020 12:09:08 MainProcess     MainThread      config          check_config_choices      DEBUG    Checking config choices
04/29/2020 12:09:08 MainProcess     MainThread      config          check_config_choices      DEBUG    Checked config choices
04/29/2020 12:09:08 MainProcess     MainThread      config          validate_config           DEBUG    Validated config
04/29/2020 12:09:08 MainProcess     MainThread      config          handle_config             DEBUG    Handled config
04/29/2020 12:09:08 MainProcess     MainThread      config          __init__                  DEBUG    Initialized: Config
04/29/2020 12:09:08 MainProcess     MainThread      _base           set_config                DEBUG    Config: {}
04/29/2020 12:09:08 MainProcess     MainThread      _base           __init__                  DEBUG    config: {}
04/29/2020 12:09:08 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized Color
04/29/2020 12:09:08 MainProcess     MainThread      convert         _load_plugins             DEBUG    Loaded plugins: {'box': <plugins.convert.mask.box_blend.Mask object at 0x00000260FBEEC608>, 'mask': <plugins.convert.mask.mask_blend.Mask object at 0x00000260FBD4C108>, 'color': <plugins.convert.color.avg_color.Color object at 0x00000260FBEE7548>, 'seamless': None, 'scaling': None}
04/29/2020 12:09:08 MainProcess     MainThread      convert         __init__                  DEBUG    Initialized Converter
04/29/2020 12:09:08 MainProcess     MainThread      convert         __init__                  DEBUG    Initialized Convert
04/29/2020 12:09:08 MainProcess     MainThread      convert         process                   DEBUG    Starting Conversion
04/29/2020 12:09:08 MainProcess     MainThread      convert         _convert_images           DEBUG    Converting images
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager getting: 'convert_out'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager got: 'convert_out'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager getting: 'patch'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager got: 'patch'
04/29/2020 12:09:08 MainProcess     MainThread      convert         _pool_processes           DEBUG    1
04/29/2020 12:09:08 MainProcess     MainThread      multithreading  __init__                  DEBUG    Initializing MultiThread: (target: 'patch', thread_count: 1)
04/29/2020 12:09:08 MainProcess     MainThread      multithreading  __init__                  TRACE    args: (<queue.Queue object at 0x00000260F5983788>, <queue.Queue object at 0x00000260F5983588>), kwargs: {}
04/29/2020 12:09:08 MainProcess     MainThread      multithreading  __init__                  DEBUG    Initialized MultiThread: 'patch'
04/29/2020 12:09:08 MainProcess     MainThread      multithreading  start                     DEBUG    Starting thread(s): 'patch'
04/29/2020 12:09:08 MainProcess     MainThread      multithreading  start                     DEBUG    Starting thread 1 of 1: 'patch_0'
04/29/2020 12:09:08 MainProcess     patch_0         convert         process                   DEBUG    Starting convert process. (in_queue: <queue.Queue object at 0x00000260F5983788>, out_queue: <queue.Queue object at 0x00000260F5983588>)
04/29/2020 12:09:08 MainProcess     MainThread      multithreading  start                     DEBUG    Started all threads 'patch': 1
04/29/2020 12:09:08 MainProcess     patch_0         convert         process                   DEBUG    EOF Received
04/29/2020 12:09:08 MainProcess     MainThread      convert         _convert_images           DEBUG    DiskIO completion event set. Joining Pool
04/29/2020 12:09:08 MainProcess     patch_0         convert         process                   DEBUG    Patch queue finished
04/29/2020 12:09:08 MainProcess     MainThread      multithreading  join                      DEBUG    Joining Threads: 'patch'
04/29/2020 12:09:08 MainProcess     patch_0         convert         process                   DEBUG    Putting EOF back to in_queue
04/29/2020 12:09:08 MainProcess     MainThread      multithreading  join                      DEBUG    Joining Thread: 'patch_0'
04/29/2020 12:09:08 MainProcess     patch_0         convert         process                   DEBUG    Completed convert process
04/29/2020 12:09:08 MainProcess     MainThread      multithreading  join                      DEBUG    Joined all Threads: 'patch'
04/29/2020 12:09:08 MainProcess     MainThread      convert         _convert_images           DEBUG    Putting EOF
04/29/2020 12:09:08 MainProcess     MainThread      convert         _convert_images           DEBUG    Converted images
04/29/2020 12:09:08 MainProcess     MainThread      multithreading  join                      DEBUG    Joining Threads: '_save'
04/29/2020 12:09:08 MainProcess     MainThread      multithreading  join                      DEBUG    Joining Thread: '_save_0'
04/29/2020 12:09:08 MainProcess     MainThread      multithreading  join                      DEBUG    Joined all Threads: '_save'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   terminate_queues          DEBUG    QueueManager terminating all queues
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   flush_queue               DEBUG    QueueManager flushing: 'ImagesLoader'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   flush_queue               DEBUG    QueueManager flushing: 'convert_in'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   flush_queue               DEBUG    QueueManager flushing: 'convert_out'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   flush_queue               DEBUG    QueueManager flushing: 'patch'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   flush_queues              DEBUG    QueueManager flushed all queues
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   terminate_queues          DEBUG    QueueManager terminating: 'ImagesLoader'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   terminate_queues          DEBUG    QueueManager terminating: 'convert_in'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   terminate_queues          DEBUG    QueueManager terminating: 'convert_out'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   terminate_queues          DEBUG    QueueManager terminating: 'patch'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   terminate_queues          DEBUG    QueueManager terminated all queues
04/29/2020 12:09:08 MainProcess     MainThread      fsmedia         finalize                  INFO     -------------------------
04/29/2020 12:09:08 MainProcess     MainThread      fsmedia         finalize                  INFO     Images found:        0
04/29/2020 12:09:08 MainProcess     MainThread      fsmedia         finalize                  INFO     Faces detected:      0
04/29/2020 12:09:08 MainProcess     MainThread      fsmedia         finalize                  INFO     -------------------------
04/29/2020 12:09:08 MainProcess     MainThread      fsmedia         finalize                  INFO     Process Succesfully Completed. Shutting Down...
04/29/2020 12:09:08 MainProcess     MainThread      convert         process                   DEBUG    Completed Conversion
04/29/2020 12:09:08 MainProcess     MainThread      utils           safe_shutdown             DEBUG    Safely shutting down
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   terminate_queues          DEBUG    QueueManager terminating all queues
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   flush_queue               DEBUG    QueueManager flushing: 'ImagesLoader'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   flush_queue               DEBUG    QueueManager flushing: 'convert_in'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   flush_queue               DEBUG    QueueManager flushing: 'convert_out'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   flush_queue               DEBUG    QueueManager flushing: 'patch'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   flush_queues              DEBUG    QueueManager flushed all queues
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   terminate_queues          DEBUG    QueueManager terminating: 'ImagesLoader'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   terminate_queues          DEBUG    QueueManager terminating: 'convert_in'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   terminate_queues          DEBUG    QueueManager terminating: 'convert_out'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   terminate_queues          DEBUG    QueueManager terminating: 'patch'
04/29/2020 12:09:08 MainProcess     MainThread      queue_manager   terminate_queues          DEBUG    QueueManager terminated all queues
04/29/2020 12:09:08 MainProcess     MainThread      utils           safe_shutdown             DEBUG    Cleanup complete. Shutting down queue manager and exiting