Error converting (bad object header version number)

Getting errors or found a bug when converting faces from a trained model? Post about them here


Forum rules

Read the FAQs and search the forum before posting a new topic.

This forum is for reporting errors with the Convert process. If you want to get tips, or better understand the Convert process, then you should look in the Convert Discussion forum.

Please mark any answers that fixed your problems so others can find the solutions.

Locked
User avatar
Antipope1
Posts: 35
Joined: Thu Jul 02, 2020 10:51 am
Has thanked: 6 times
Been thanked: 3 times

Error converting (bad object header version number)

Post by Antipope1 »

I tried to convert this evening and kept getting this error.

Code: Select all

1 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.dfl_sae
 2 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: dlight_defaults.py, module_path: plugins.train.model, plugin_type: model
 3 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.dlight_defaults
 4 
 
09/28/2020 01:03:19 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.')
 5 
 
09/28/2020 01:03:19 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)
 6 
 
09/28/2020 01:03:19 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)
 7 
 
09/28/2020 01:03:19 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)
 8 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.dlight
 9 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: original_defaults.py, module_path: plugins.train.model, plugin_type: model
 10 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.original_defaults
 11 
 
09/28/2020 01:03:19 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.')
 12 
 
09/28/2020 01:03:19 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)
 13 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.original
 14 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: realface_defaults.py, module_path: plugins.train.model, plugin_type: model
 15 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.realface_defaults
 16 
 
09/28/2020 01:03:19 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.')
 17 
 
09/28/2020 01:03:19 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)
 18 
 
09/28/2020 01:03:19 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)
 19 
 
09/28/2020 01:03:19 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)
 20 
 
09/28/2020 01:03:19 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)
 21 
 
09/28/2020 01:03:19 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)
 22 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.realface
 23 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: unbalanced_defaults.py, module_path: plugins.train.model, plugin_type: model
 24 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.unbalanced_defaults
 25 
 
09/28/2020 01:03:19 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.')
 26 
 
09/28/2020 01:03:19 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)
 27 
 
09/28/2020 01:03:19 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)
 28 
 
09/28/2020 01:03:19 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)
 29 
 
09/28/2020 01:03:19 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)
 30 
 
09/28/2020 01:03:19 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)
 31 
 
09/28/2020 01:03:19 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)
 32 
 
09/28/2020 01:03:19 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)
 33 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.unbalanced
 34 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: villain_defaults.py, module_path: plugins.train.model, plugin_type: model
 35 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.model.villain_defaults
 36 
 
09/28/2020 01:03:19 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. Don't try to run this if you have a small GPU.\n\nNB: Unless specifically stated, values changed here will only take effect when creating a new model.')
 37 
 
09/28/2020 01:03:19 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)
 38 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: model.villain
 39 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: original_defaults.py, module_path: plugins.train.trainer, plugin_type: trainer
 40 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.train.trainer.original_defaults
 41 
 
09/28/2020 01:03:19 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!')
 42 
 
09/28/2020 01:03:19 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)
 43 
 
09/28/2020 01:03:19 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)
 44 
 
09/28/2020 01:03:19 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)
 45 
 
09/28/2020 01:03:19 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)
 46 
 
09/28/2020 01:03:19 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)
 47 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'trainer.original', title: 'disable_warp', datatype: '<class 'bool'>', default: 'False', info: 'Disable warp augmentation. Warping is integral to the Neural Network training. If you decide to disable warping, you should only do so towards the end of a model's training session.', rounding: 'None', min_max: None, choices: None, gui_radio: False, fixed: False, group: image augmentation)
 48 
 
09/28/2020 01:03:19 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-flip' option is enabled', rounding: '1', min_max: (0, 75), choices: None, gui_radio: False, fixed: True, group: color augmentation)
 49 
 
09/28/2020 01:03:19 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-flip' option is enabled', rounding: '1', min_max: (0, 50), choices: None, gui_radio: False, fixed: True, group: color augmentation)
 50 
 
09/28/2020 01:03:19 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)
 51 
 
09/28/2020 01:03:19 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)
 52 
 
09/28/2020 01:03:19 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: trainer.original
 53 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          handle_config             DEBUG    Handling config
 54 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          check_exists              DEBUG    Config file exists: 'I:\faceswap\config\train.ini'
 55 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          load_config               VERBOSE  Loading config: 'I:\faceswap\config\train.ini'
 56 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          validate_config           DEBUG    Validating config
 57 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          check_config_change       DEBUG    Default config has not changed
 58 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          check_config_choices      DEBUG    Checking config choices
 59 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          check_config_choices      DEBUG    Checked config choices
 60 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          validate_config           DEBUG    Validated config
 61 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          handle_config             DEBUG    Handled config
 62 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          __init__                  DEBUG    Initialized: Config
 63 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'learning_rate')
 64 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'float'>, value: 5e-05)
 65 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'allow_growth')
 66 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'bool'>, value: False)
 67 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'global', option: 'convert_batchsize')
 68 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'int'>, value: 16)
 69 
 
09/28/2020 01:03:19 MainProcess     MainThread      config          changeable_items          DEBUG    Alterable for existing models: {'learning_rate': 5e-05, 'allow_growth': False, 'convert_batchsize': 16}
 70 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing State: (model_dir: 'I:\Faceswap Resources\sio1\FaceSwap\Models', model_name: 'realface', config_changeable_items: '{'learning_rate': 5e-05, 'allow_growth': False, 'convert_batchsize': 16}', no_logs: False, training_image_size: '256'
 71 
 
09/28/2020 01:03:19 MainProcess     MainThread      serializer      get_serializer            DEBUG    <lib.serializer._JSONSerializer object at 0x000001CD3742BC40>
 72 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _load                     DEBUG    Loading State
 73 
 
09/28/2020 01:03:19 MainProcess     MainThread      serializer      load                      DEBUG    filename: I:\Faceswap Resources\sio1\FaceSwap\Models\realface_state.json
 74 
 
09/28/2020 01:03:19 MainProcess     MainThread      serializer      load                      DEBUG    stored data type: <class 'bytes'>
 75 
 
09/28/2020 01:03:19 MainProcess     MainThread      serializer      unmarshal                 DEBUG    data type: <class 'bytes'>
 76 
 
09/28/2020 01:03:19 MainProcess     MainThread      serializer      unmarshal                 DEBUG    returned data type: <class 'dict'>
 77 
 
09/28/2020 01:03:19 MainProcess     MainThread      serializer      load                      DEBUG    data type: <class 'dict'>
 78 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _load                     DEBUG    Loaded state: {'name': 'realface', 'sessions': {'1': {'timestamp': 1600818874.1031203, 'no_logs': False, 'loss_names': ['total', 'face_a', 'face_b'], 'batchsize': 16, 'iterations': 56680, 'config': {'learning_rate': 5e-05, 'allow_growth': False, 'convert_batchsize': 16}}, '2': {'timestamp': 1600880535.6287405, 'no_logs': False, 'loss_names': ['total', 'face_a', 'face_b'], 'batchsize': 16, 'iterations': 29031, 'config': {'learning_rate': 5e-05, 'allow_growth': False, 'convert_batchsize': 16}}, '3': {'timestamp': 1600893489.5451026, 'no_logs': False, 'loss_names': ['total', 'face_a', 'face_b'], 'batchsize': 16, 'iterations': 1, 'config': {'learning_rate': 5e-05, 'allow_growth': False, 'convert_batchsize': 16}}}, 'lowest_avg_loss': {'a': 0.03331407456099987, 'b': 0.03500699474662542}, 'iterations': 85712, 'training_size': 256, 'config': {'coverage': 84.68, 'optimizer': 'adam', 'learning_rate': 5e-05, 'allow_growth': False, 'mixed_precision': True, 'convert_batchsize': 16, 'loss_function': 'ssim', 'mask_loss_function': 'mse', 'l2_reg_term': 100, 'eye_multiplier': 6, 'mouth_multiplier': 4, 'penalized_mask_loss': True, 'mask_type': 'extended', 'mask_blur_kernel': 3, 'mask_threshold': 4, 'learn_mask': False, 'input_size': 64, 'output_size': 128, 'dense_nodes': 1536, 'complexity_encoder': 128, 'complexity_decoder': 512}}
 79 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _update_legacy_config     DEBUG    Checking for legacy state file update
 80 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _update_legacy_config     DEBUG    Legacy item 'dssim_loss' not in config. Skipping update
 81 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _update_legacy_config     DEBUG    State file updated for legacy config: False
 82 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _replace_config           DEBUG    Replacing config. Old config: {'coverage': 68.75, 'optimizer': 'adam', 'learning_rate': 5e-05, 'allow_growth': False, 'mixed_precision': False, 'convert_batchsize': 16, 'loss_function': 'ssim', 'mask_loss_function': 'mse', 'l2_reg_term': 100, 'eye_multiplier': 3, 'mouth_multiplier': 2, 'penalized_mask_loss': True, 'mask_type': 'extended', 'mask_blur_kernel': 3, 'mask_threshold': 4, 'learn_mask': False, 'input_size': 64, 'output_size': 128, 'dense_nodes': 1536, 'complexity_encoder': 128, 'complexity_decoder': 512}
 83 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _replace_config           DEBUG    Replaced config. New config: {'coverage': 84.68, 'optimizer': 'adam', 'learning_rate': 5e-05, 'allow_growth': False, 'mixed_precision': True, 'convert_batchsize': 16, 'loss_function': 'ssim', 'mask_loss_function': 'mse', 'l2_reg_term': 100, 'eye_multiplier': 6, 'mouth_multiplier': 4, 'penalized_mask_loss': True, 'mask_type': 'extended', 'mask_blur_kernel': 3, 'mask_threshold': 4, 'learn_mask': False, 'input_size': 64, 'output_size': 128, 'dense_nodes': 1536, 'complexity_encoder': 128, 'complexity_decoder': 512}
 84 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _replace_config           INFO     Using configuration saved in state file
 85 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _new_session_id           DEBUG    4
 86 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _create_new_session       DEBUG    Creating new session. id: 4
 87 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized State:
 88 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing _Settings: (arguments: Namespace(alignments_path='I:\\Faceswap Resources\\sio1\\FaceSwap\\InputA\\Video\\masshrt\\Untitled Project_alignments.fsa', colab=False, color_adjustment='avg-color', configfile=None, distributed=False, exclude_gpus=None, filter=None, frame_ranges=None, func=<bound method ScriptExecutor.execute_script of <lib.cli.launcher.ScriptExecutor object at 0x000001CD23C16DF0>>, input_aligned_dir=None, input_dir='I:\\Faceswap Resources\\sio1\\FaceSwap\\InputA\\Video\\masshrt\\Untitled Project.mp4', jobs=0, keep_unchanged=False, logfile=None, loglevel='INFO', mask_type='extended', model_dir='I:\\Faceswap Resources\\sio1\\FaceSwap\\Models', nfilter=None, on_the_fly=False, output_dir='I:\\Faceswap Resources\\sio1\\FaceSwap\\Convert', output_scale=100, redirect_gui=True, ref_threshold=0.4, reference_video=None, scaling='none', singleprocess=False, swap_model=False, trainer=None, writer='ffmpeg'), mixed_precision: True, allow_growth: False, is_predict: True)
 89 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _set_tf_settings          DEBUG    Not setting any specific Tensorflow settings
 90 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _set_keras_mixed_precision DEBUG    use_mixed_precision: False, skip_check: False
 91 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _set_keras_mixed_precision DEBUG    Not enabling 'mixed_precision' (backend: nvidia, use_mixed_precision: False)
 92 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _get_strategy             DEBUG    Using strategy: <tensorflow.python.distribute.distribute_lib._DefaultDistributionStrategy object at 0x000001CD3742B6D0>
 93 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized _Settings
 94 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           __init__                  DEBUG    Initializing _Loss
 95 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized: _Loss
 96 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized ModelBase (Model)
 97 
 
09/28/2020 01:03:19 MainProcess     MainThread      realface        check_input_output        DEBUG    Input and output sizes are valid
 98 
 
09/28/2020 01:03:19 MainProcess     MainThread      realface        get_dense_width_upscalers_numbers DEBUG    dense_width: 4, upscalers_no: 5
 99 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           strategy_scope            DEBUG    Using strategy scope: <tensorflow.python.distribute.distribute_lib._DefaultDistributionContext object at 0x000001CD320311C0>
 100 
 
09/28/2020 01:03:19 MainProcess     MainThread      _base           _load                     DEBUG    Loading model: I:\Faceswap Resources\sio1\FaceSwap\Models\realface.h5
 101 
 
Traceback (most recent call last):
 102 
 
  File "I:\faceswap\lib\cli\launcher.py", line 181, in execute_script
 103 
 
process = script(arguments)
 104 
 
  File "I:\faceswap\scripts\convert.py", line 60, in __init__
 105 
 
self._predictor = Predict(self._disk_io.load_queue, self._queue_size, arguments)
 106 
 
  File "I:\faceswap\scripts\convert.py", line 655, in __init__
 107 
 
self._model = self._load_model()
 108 
 
  File "I:\faceswap\scripts\convert.py", line 734, in _load_model
 109 
 
model.build()
 110 
 
  File "I:\faceswap\plugins\train\model\_base.py", line 260, in build
 111 
 
model = self._io._load()  # pylint:disable=protected-access
 112 
 
  File "I:\faceswap\plugins\train\model\_base.py", line 521, in _load
 113 
 
model = load_model(self._filename, compile=False)
 114 
 
  File "C:\Users\Matt\MiniConda3\envs\faceswap\lib\site-packages\tensorflow\python\keras\saving\save.py", line 184, in load_model
 115 
 
return hdf5_format.load_model_from_hdf5(filepath, custom_objects, compile)
 116 
 
  File "C:\Users\Matt\MiniConda3\envs\faceswap\lib\site-packages\tensorflow\python\keras\saving\hdf5_format.py", line 166, in load_model_from_hdf5
 117 
 
f = h5py.File(filepath, mode='r')
 118 
 
  File "C:\Users\Matt\MiniConda3\envs\faceswap\lib\site-packages\h5py\_hl\files.py", line 406, in __init__
 119 
 
fid = make_fid(name, mode, userblock_size,
 120 
 
  File "C:\Users\Matt\MiniConda3\envs\faceswap\lib\site-packages\h5py\_hl\files.py", line 173, in make_fid
 121 
 
fid = h5f.open(name, flags, fapl=fapl)
 122 
 
  File "h5py\_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
 123 
 
  File "h5py\_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
 124 
 
  File "h5py\h5f.pyx", line 88, in h5py.h5f.open
 125 
 
OSError: Unable to open file (bad object header version number)
 126 
 
 127 
 
============ System Information ============
 128 
 
encoding:            cp1252
 129 
 
git_branch:          master
 130 
 
git_commits:         8861101 Setup.py - Minor change to cudnn locator
 131 
 
gpu_cuda:            No global version found. Check Conda packages for Conda Cuda
 132 
 
gpu_cudnn:           No global version found. Check Conda packages for Conda cuDNN
 133 
 
gpu_devices:         GPU_0: GeForce RTX 2060 SUPER
 134 
 
gpu_devices_active:  GPU_0
 135 
 
gpu_driver:          456.38
 136 
 
gpu_vram:            GPU_0: 8192MB
 137 
 
os_machine:          AMD64
 138 
 
os_platform:         Windows-10-10.0.18362-SP0
 139 
 
os_release:          10
 140 
 
py_command:          I:\faceswap\faceswap.py convert -i I:/Faceswap Resources/sio1/FaceSwap/InputA/Video/masshrt/Untitled Project.mp4 -o I:/Faceswap Resources/sio1/FaceSwap/Convert -al I:/Faceswap Resources/sio1/FaceSwap/InputA/Video/masshrt/Untitled Project_alignments.fsa -m I:/Faceswap Resources/sio1/FaceSwap/Models -c avg-color -M extended -sc none -w ffmpeg -osc 100 -l 0.4 -j 0 -L INFO -gui
 141 
 
py_conda_version:    conda 4.8.5
 142 
 
py_implementation:   CPython
 143 
 
py_version:          3.8.5
 144 
 
py_virtual_env:      True
 145 
 
sys_cores:           4
 146 
 
sys_processor:       AMD64 Family 23 Model 17 Stepping 0, AuthenticAMD
 147 
 
sys_ram:             Total: 32715MB, Available: 27542MB, Used: 5172MB, Free: 27542MB
 148 
 
 149 
 
=============== Pip Packages ===============
 150 
 
absl-py==0.10.0
 151 
 
astunparse==1.6.3
 152 
 
cachetools==4.1.1
 153 
 
certifi==2020.6.20
 154 
 
chardet==3.0.4
 155 
 
cycler==0.10.0
 156 
 
fastcluster==1.1.26
 157 
 
ffmpy==0.2.3
 158 
 
gast==0.3.3
 159 
 
google-auth==1.21.3
 160 
 
google-auth-oauthlib==0.4.1
 161 
 
google-pasta==0.2.0
 162 
 
grpcio==1.32.0
 163 
 
h5py==2.10.0
 164 
 
idna==2.10
 165 
 
imageio @ file:///tmp/build/80754af9/imageio_1594161405741/work
 166 
 
imageio-ffmpeg @ file:///home/conda/feedstock_root/build_artifacts/imageio-ffmpeg_1589202782679/work
 167 
 
joblib @ file:///tmp/build/80754af9/joblib_1594236160679/work
 168 
 
Keras-Preprocessing==1.1.2
 169 
 
kiwisolver==1.2.0
 170 
 
Markdown==3.2.2
 171 
 
matplotlib @ file:///C:/ci/matplotlib-base_1592837548929/work
 172 
 
mkl-fft==1.2.0
 173 
 
mkl-random==1.1.1
 174 
 
mkl-service==2.3.0
 175 
 
numpy==1.18.5
 176 
 
nvidia-ml-py3 @ git+https://github.com/deepfakes/nvidia-ml-py3.git@6fc29ac84b32bad877f078cb4a777c1548a00bf6
 177 
 
oauthlib==3.1.0
 178 
 
olefile==0.46
 179 
 
opencv-python==4.4.0.44
 180 
 
opt-einsum==3.3.0
 181 
 
pathlib==1.0.1
 182 
 
Pillow @ file:///C:/ci/pillow_1594298230227/work
 183 
 
protobuf==3.13.0
 184 
 
psutil @ file:///C:/ci/psutil_1598370330503/work
 185 
 
pyasn1==0.4.8
 186 
 
pyasn1-modules==0.2.8
 187 
 
pyparsing==2.4.7
 188 
 
python-dateutil==2.8.1
 189 
 
pywin32==227
 190 
 
requests==2.24.0
 191 
 
requests-oauthlib==1.3.0
 192 
 
rsa==4.6
 193 
 
scikit-learn @ file:///C:/ci/scikit-learn_1598377018496/work
 194 
 
scipy @ file:///C:/ci/scipy_1592916963468/work
 195 
 
sip==4.19.13
 196 
 
six==1.15.0
 197 
 
tensorboard==2.2.2
 198 
 
tensorboard-plugin-wit==1.7.0
 199 
 
tensorflow-gpu==2.2.1
 200 
 
tensorflow-gpu-estimator==2.2.0
 201 
 
termcolor==1.1.0
 202 
 
threadpoolctl @ file:///tmp/tmp9twdgx9k/threadpoolctl-2.1.0-py3-none-any.whl
 203 
 
tornado==6.0.4
 204 
 
tqdm @ file:///tmp/build/80754af9/tqdm_1600709023549/work
 205 
 
urllib3==1.25.10
 206 
 
Werkzeug==1.0.1
 207 
 
wincertstore==0.2
 208 
 
wrapt==1.12.1
 209 
 
 210 
 
============== Conda Packages ==============
 211 
 
# packages in environment at C:\Users\Matt\MiniConda3\envs\faceswap:
 212 
 
#
 213 
 
# Name                    Version                   Build  Channel
 214 
 
absl-py                   0.10.0                   pypi_0    pypi
 215 
 
astunparse                1.6.3                    pypi_0    pypi
 216 
 
blas                      1.0                         mkl  
217 ca-certificates 2020.7.22 0
218 cachetools 4.1.1 pypi_0 pypi 219 certifi 2020.6.20 py38_0
220 chardet 3.0.4 pypi_0 pypi 221 cudatoolkit 10.1.243 h74a9793_0
222 cudnn 7.6.5 cuda10.1_0
223 cycler 0.10.0 py38_0
224 fastcluster 1.1.26 py38hbe40bda_1 conda-forge 225 ffmpeg 4.3.1 ha925a31_0 conda-forge 226 ffmpy 0.2.3 pypi_0 pypi 227 freetype 2.10.2 hd328e21_0
228 gast 0.3.3 pypi_0 pypi 229 git 2.23.0 h6bb4b03_0
230 google-auth 1.21.3 pypi_0 pypi 231 google-auth-oauthlib 0.4.1 pypi_0 pypi 232 google-pasta 0.2.0 pypi_0 pypi 233 grpcio 1.32.0 pypi_0 pypi 234 h5py 2.10.0 pypi_0 pypi 235 icc_rt 2019.0.0 h0cc432a_1
236 icu 58.2 ha925a31_3
237 idna 2.10 pypi_0 pypi 238 imageio 2.9.0 py_0
239 imageio-ffmpeg 0.4.2 py_0 conda-forge 240 intel-openmp 2020.2 254
241 joblib 0.16.0 py_0
242 jpeg 9b hb83a4c4_2
243 keras-preprocessing 1.1.2 pypi_0 pypi 244 kiwisolver 1.2.0 py38h74a9793_0
245 libpng 1.6.37 h2a8f88b_0
246 libtiff 4.1.0 h56a325e_1
247 lz4-c 1.9.2 h62dcd97_1
248 markdown 3.2.2 pypi_0 pypi 249 matplotlib 3.2.2 0
250 matplotlib-base 3.2.2 py38h64f37c6_0
251 mkl 2020.2 256
252 mkl-service 2.3.0 py38hb782905_0
253 mkl_fft 1.2.0 py38h45dec08_0
254 mkl_random 1.1.1 py38h47e9c7a_0
255 numpy 1.18.5 pypi_0 pypi 256 nvidia-ml-py3 7.352.1 pypi_0 pypi 257 oauthlib 3.1.0 pypi_0 pypi 258 olefile 0.46 py_0
259 opencv-python 4.4.0.44 pypi_0 pypi 260 openssl 1.1.1h he774522_0
261 opt-einsum 3.3.0 pypi_0 pypi 262 pathlib 1.0.1 py_1
263 pillow 7.2.0 py38hcc1f983_0
264 pip 20.2.2 py38_0
265 protobuf 3.13.0 pypi_0 pypi 266 psutil 5.7.2 py38he774522_0
267 pyasn1 0.4.8 pypi_0 pypi 268 pyasn1-modules 0.2.8 pypi_0 pypi 269 pyparsing 2.4.7 py_0
270 pyqt 5.9.2 py38ha925a31_4
271 python 3.8.5 h5fd99cc_1
272 python-dateutil 2.8.1 py_0
273 python_abi 3.8 1_cp38 conda-forge 274 pywin32 227 py38he774522_1
275 qt 5.9.7 vc14h73c81de_0
276 requests 2.24.0 pypi_0 pypi 277 requests-oauthlib 1.3.0 pypi_0 pypi 278 rsa 4.6 pypi_0 pypi 279 scikit-learn 0.23.2 py38h47e9c7a_0
280 scipy 1.5.0 py38h9439919_0
281 setuptools 49.6.0 py38_0
282 sip 4.19.13 py38ha925a31_0
283 six 1.15.0 py_0
284 sqlite 3.33.0 h2a8f88b_0
285 tensorboard 2.2.2 pypi_0 pypi 286 tensorboard-plugin-wit 1.7.0 pypi_0 pypi 287 tensorflow-gpu 2.2.1 pypi_0 pypi 288 tensorflow-gpu-estimator 2.2.0 pypi_0 pypi 289 termcolor 1.1.0 pypi_0 pypi 290 threadpoolctl 2.1.0 pyh5ca1d4c_0
291 tk 8.6.10 he774522_0
292 tornado 6.0.4 py38he774522_1
293 tqdm 4.49.0 py_0
294 urllib3 1.25.10 pypi_0 pypi 295 vc 14.1 h0510ff6_4
296 vs2015_runtime 14.16.27012 hf0eaf9b_3
297 werkzeug 1.0.1 pypi_0 pypi 298 wheel 0.35.1 py_0
299 wincertstore 0.2 py38_0
300 wrapt 1.12.1 pypi_0 pypi 301 xz 5.2.5 h62dcd97_0
302 zlib 1.2.11 h62dcd97_4
303 zstd 1.4.5 h04227a9_0
304 305 ================= Configs ================== 306 --------- .faceswap --------- 307 backend: nvidia 308 309 --------- convert.ini --------- 310 311 [color.color_transfer] 312 clip: True 313 preserve_paper: True 314 315 [color.manual_balance] 316 colorspace: HSV 317 balance_1: 0.0 318 balance_2: 0.0 319 balance_3: 0.0 320 contrast: 0.0 321 brightness: 0.0 322 323 [color.match_hist] 324 threshold: 99.0 325 326 [mask.box_blend] 327 type: gaussian 328 distance: 11.0 329 radius: 5.0 330 passes: 1 331 332 [mask.mask_blend] 333 type: normalized 334 kernel_size: 3 335 passes: 4 336 threshold: 4 337 erosion: 0.0 338 339 [scaling.sharpen] 340 method: unsharp_mask 341 amount: 150 342 radius: 0.3 343 threshold: 5.0 344 345 [writer.ffmpeg] 346 container: mp4 347 codec: libx264 348 crf: 23 349 preset: medium 350 tune: none 351 profile: auto 352 level: auto 353 skip_mux: False 354 355 [writer.gif] 356 fps: 25 357 loop: 0 358 palettesize: 256 359 subrectangles: False 360 361 [writer.opencv] 362 format: png 363 draw_transparent: False 364 jpg_quality: 75 365 png_compress_level: 3 366 367 [writer.pillow] 368 format: png 369 draw_transparent: False 370 optimize: False 371 gif_interlace: True 372 jpg_quality: 75 373 png_compress_level: 3 374 tif_compression: tiff_deflate 375 376 --------- extract.ini --------- 377 378 [global] 379 allow_growth: False 380 381 [align.fan] 382 batch-size: 12 383 384 [detect.cv2_dnn] 385 confidence: 50 386 387 [detect.mtcnn] 388 minsize: 20 389 threshold_1: 0.6 390 threshold_2: 0.7 391 threshold_3: 0.7 392 scalefactor: 0.709 393 batch-size: 8 394 395 [detect.s3fd] 396 confidence: 70 397 batch-size: 4 398 399 [mask.unet_dfl] 400 batch-size: 8 401 402 [mask.vgg_clear] 403 batch-size: 6 404 405 [mask.vgg_obstructed] 406 batch-size: 2 407 408 --------- gui.ini --------- 409 410 [global] 411 fullscreen: True 412 tab: extract 413 options_panel_width: 30 414 console_panel_height: 20 415 icon_size: 14 416 font: default 417 font_size: 9 418 autosave_last_session: prompt 419 timeout: 120 420 auto_load_model_stats: True 421 422 --------- train.ini --------- 423 424 [global] 425 coverage: 68.75 426 icnr_init: False 427 conv_aware_init: False 428 optimizer: adam 429 learning_rate: 5e-05 430 reflect_padding: False 431 allow_growth: False 432 mixed_precision: False 433 convert_batchsize: 16 434 435 [global.loss] 436 loss_function: ssim 437 mask_loss_function: mse 438 l2_reg_term: 100 439 eye_multiplier: 3 440 mouth_multiplier: 2 441 penalized_mask_loss: True 442 mask_type: extended 443 mask_blur_kernel: 3 444 mask_threshold: 4 445 learn_mask: False 446 447 [model.dfl_h128] 448 lowmem: False 449 450 [model.dfl_sae] 451 input_size: 128 452 clipnorm: True 453 architecture: df 454 autoencoder_dims: 0 455 encoder_dims: 42 456 decoder_dims: 21 457 multiscale_decoder: False 458 459 [model.dlight] 460 features: best 461 details: good 462 output_size: 256 463 464 [model.original] 465 lowmem: False 466 467 [model.realface] 468 input_size: 64 469 output_size: 128 470 dense_nodes: 1536 471 complexity_encoder: 128 472 complexity_decoder: 512 473 474 [model.unbalanced] 475 input_size: 128 476 lowmem: False 477 clipnorm: True 478 nodes: 1024 479 complexity_encoder: 128 480 complexity_decoder_a: 384 481 complexity_decoder_b: 512 482 483 [model.villain] 484 lowmem: False 485 486 [trainer.original] 487 preview_images: 14 488 zoom_amount: 5 489 rotation_range: 10 490 shift_range: 5 491 flip_chance: 50 492 disable_warp: False color_lightness: 30 color_ab: 8 color_clahe_chance: 50 color_clahe_max_size: 4

What could be the problem?
I initially realised I needed an update so I did that and it didn't work, I tried deleting all of faceswap, conda etc. Reinstalled And that made no difference.
I also tried ffmpeg and opencv with no luck.

by bryanlyon » Mon Sep 28, 2020 2:58 am

This looks like a corrupt model file. Try using the restore tool to load from a backup.

Go to full post
The beginning of the end.
User avatar
bryanlyon
Site Admin
Posts: 793
Joined: Fri Jul 12, 2019 12:49 am
Answers: 44
Location: San Francisco
Has thanked: 4 times
Been thanked: 218 times
Contact:

Re: Error converting (bad object header version number)

Post by bryanlyon »

This looks like a corrupt model file. Try using the restore tool to load from a backup.

Locked