I reinstalled python, recreated a new anaconda environment, let it update packages, then I started up my first training session from a previous model and I began to train a brand new model (I did not use any previously created model) for 15 hours straight. When I clicked "stop", then clicked "Train" (I didn't even close faceswap or restart my computer) it now gives this error that I keep getting no matter what I do. I retried restarting my faceswap but it didn't work
Code: Select all
File "C:\Users\pfftdammitchris\faceswap\plugins\train\model\_base.py", line 244, in build
self.load_models(swapped=False)
File "C:\Users\pfftdammitchris\faceswap\plugins\train\model\_base.py", line 456, in load_models
is_loaded = network.load(fullpath=model_mapping[network.side][network.type])
File "C:\Users\pfftdammitchris\faceswap\plugins\train\model\_base.py", line 834, in load
network = load_model(self.filename, custom_objects=get_custom_objects())
File "C:\Users\pfftdammitchris\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\saving.py", line 419, in load_model
model = _deserialize_model(f, custom_objects, compile)
File "C:\Users\pfftdammitchris\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\saving.py", line 224, in _deserialize_model
model_config = json.loads(model_config.decode('utf-8'))
AttributeError: 'str' object has no attribute 'decode'
05/22/2023 13:14:53 CRITICAL An unexpected crash has occurred. Crash report written to 'C:\Users\pfftdammitchris\faceswap\crash_report.2023.05.22.131449461273.log'. You MUST provide this file if seeking assistance. Please verify you are running the latest version of faceswap before reporting
Process exited.
Here is my crash report:
Code: Select all
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks __init__ DEBUG Initializing NNBlocks: (use_icnr_init: False, use_convaware_init: False, use_reflect_padding: False, first_run: False)
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks __init__ DEBUG Initialized NNBlocks
05/22/2023 13:03:21 MainProcess _training_0 _base name DEBUG model name: 'original'
05/22/2023 13:03:21 MainProcess _training_0 _base rename_legacy DEBUG Renaming legacy files
05/22/2023 13:03:21 MainProcess _training_0 _base name DEBUG model name: 'original'
05/22/2023 13:03:21 MainProcess _training_0 _base rename_legacy DEBUG No legacy files to rename
05/22/2023 13:03:21 MainProcess _training_0 _base load_state_info DEBUG Loading Input Shape from State file
05/22/2023 13:03:21 MainProcess _training_0 _base load_state_info DEBUG Setting input shape from state file: (64, 64, 3)
05/22/2023 13:03:21 MainProcess _training_0 _base calculate_coverage_ratio DEBUG Requested coverage_ratio: 0.6875
05/22/2023 13:03:21 MainProcess _training_0 _base calculate_coverage_ratio DEBUG Final coverage_ratio: 0.6875
05/22/2023 13:03:21 MainProcess _training_0 _base __init__ DEBUG training_opts: {'alignments': {'a': 'C:\\Users\\pfftdammitchris\\Desktop\\faceswap\\input-A\\7_alignments.fsa', 'b': 'C:\\Users\\pfftdammitchris\\Desktop\\faceswap\\output-B\\alignments.fsa'}, 'preview_scaling': 0.5, 'warp_to_landmarks': False, 'augment_color': True, 'no_flip': False, 'pingpong': False, 'snapshot_interval': 25000, 'training_size': 512, 'no_logs': False, 'coverage_ratio': 0.6875, 'mask_type': None, 'mask_blur_kernel': 3, 'mask_threshold': 4, 'learn_mask': False, 'penalized_mask_loss': False}
05/22/2023 13:03:21 MainProcess _training_0 _base multiple_models_in_folder DEBUG model_files: ['original_decoder_A.h5', 'original_decoder_B.h5', 'original_encoder.h5'], retval: False
05/22/2023 13:03:21 MainProcess _training_0 original add_networks DEBUG Adding networks
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks upscale DEBUG input_tensor: input_1 Placeholder FLOAT32(<tile.Value SymbolicDim UINT64()>, 8, 8, 512), filters: 256, kernel_size: 3, use_instance_norm: False, kwargs: {})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _get_name DEBUG Generating block name: upscale_(<tile.Value SymbolicDim UINT64()>, 8, 8, 512)_0
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x0000012D0CDAB908>
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks conv2d DEBUG input_tensor: input_1 Placeholder FLOAT32(<tile.Value SymbolicDim UINT64()>, 8, 8, 512), filters: 1024, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_(<tile.Value SymbolicDim UINT64()>, 8, 8, 512)_0_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x0000012D0CDAB908>})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Using model specified initializer: <keras.initializers.VarianceScaling object at 0x0000012D0CDAB908>
05/22/2023 13:03:21 MainProcess _training_0 library _logger_callback INFO Opening device "opencl_nvidia_nvidia_geforce_rtx_3050_laptop_gpu.0"
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks upscale DEBUG input_tensor: Reshape FLOAT32(<tile.Value FloorDiv FLOAT64()>, 16, 16, 256), filters: 128, kernel_size: 3, use_instance_norm: False, kwargs: {})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _get_name DEBUG Generating block name: upscale_(<tile.Value FloorDiv FLOAT64()>, 16, 16, 256)_0
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x0000012D0CDA0D88>
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks conv2d DEBUG input_tensor: Reshape FLOAT32(<tile.Value FloorDiv FLOAT64()>, 16, 16, 256), filters: 512, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_(<tile.Value FloorDiv FLOAT64()>, 16, 16, 256)_0_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x0000012D0CDA0D88>})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Using model specified initializer: <keras.initializers.VarianceScaling object at 0x0000012D0CDA0D88>
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks upscale DEBUG input_tensor: Reshape FLOAT32(<tile.Value FloorDiv FLOAT64()>, 32, 32, 128), filters: 64, kernel_size: 3, use_instance_norm: False, kwargs: {})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _get_name DEBUG Generating block name: upscale_(<tile.Value FloorDiv FLOAT64()>, 32, 32, 128)_0
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x0000012D0CE72248>
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks conv2d DEBUG input_tensor: Reshape FLOAT32(<tile.Value FloorDiv FLOAT64()>, 32, 32, 128), filters: 256, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_(<tile.Value FloorDiv FLOAT64()>, 32, 32, 128)_0_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x0000012D0CE72248>})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Using model specified initializer: <keras.initializers.VarianceScaling object at 0x0000012D0CE72248>
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks conv2d DEBUG input_tensor: Reshape FLOAT32(<tile.Value FloorDiv FLOAT64()>, 64, 64, 64), filters: 3, kernel_size: 5, strides: (1, 1), padding: same, kwargs: {'activation': 'sigmoid', 'name': 'face_out'})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x0000012D0CE7A9C8>
05/22/2023 13:03:21 MainProcess _training_0 _base add_network DEBUG network_type: 'decoder', side: 'a', network: '<keras.engine.training.Model object at 0x0000012D0CE2B4C8>', is_output: True
05/22/2023 13:03:21 MainProcess _training_0 _base name DEBUG model name: 'original'
05/22/2023 13:03:21 MainProcess _training_0 _base add_network DEBUG name: 'decoder_a', filename: 'original_decoder_A.h5'
05/22/2023 13:03:21 MainProcess _training_0 _base __init__ DEBUG Initializing NNMeta: (filename: 'C:\Users\pfftdammitchris\Desktop\faceswap\models\bigie-2\original_decoder_A.h5', network_type: 'decoder', side: 'a', network: <keras.engine.training.Model object at 0x0000012D0CE2B4C8>, is_output: True
05/22/2023 13:03:21 MainProcess _training_0 _base __init__ DEBUG Initialized NNMeta
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks upscale DEBUG input_tensor: input_2 Placeholder FLOAT32(<tile.Value SymbolicDim UINT64()>, 8, 8, 512), filters: 256, kernel_size: 3, use_instance_norm: False, kwargs: {})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _get_name DEBUG Generating block name: upscale_(<tile.Value SymbolicDim UINT64()>, 8, 8, 512)_1
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x0000012D0CE9DC48>
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks conv2d DEBUG input_tensor: input_2 Placeholder FLOAT32(<tile.Value SymbolicDim UINT64()>, 8, 8, 512), filters: 1024, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_(<tile.Value SymbolicDim UINT64()>, 8, 8, 512)_1_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x0000012D0CE9DC48>})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Using model specified initializer: <keras.initializers.VarianceScaling object at 0x0000012D0CE9DC48>
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks upscale DEBUG input_tensor: Reshape FLOAT32(<tile.Value FloorDiv FLOAT64()>, 16, 16, 256), filters: 128, kernel_size: 3, use_instance_norm: False, kwargs: {})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _get_name DEBUG Generating block name: upscale_(<tile.Value FloorDiv FLOAT64()>, 16, 16, 256)_1
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x0000012D0CEAA048>
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks conv2d DEBUG input_tensor: Reshape FLOAT32(<tile.Value FloorDiv FLOAT64()>, 16, 16, 256), filters: 512, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_(<tile.Value FloorDiv FLOAT64()>, 16, 16, 256)_1_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x0000012D0CEAA048>})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Using model specified initializer: <keras.initializers.VarianceScaling object at 0x0000012D0CEAA048>
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks upscale DEBUG input_tensor: Reshape FLOAT32(<tile.Value FloorDiv FLOAT64()>, 32, 32, 128), filters: 64, kernel_size: 3, use_instance_norm: False, kwargs: {})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _get_name DEBUG Generating block name: upscale_(<tile.Value FloorDiv FLOAT64()>, 32, 32, 128)_1
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x0000012D0CEF5AC8>
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks conv2d DEBUG input_tensor: Reshape FLOAT32(<tile.Value FloorDiv FLOAT64()>, 32, 32, 128), filters: 256, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_(<tile.Value FloorDiv FLOAT64()>, 32, 32, 128)_1_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x0000012D0CEF5AC8>})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Using model specified initializer: <keras.initializers.VarianceScaling object at 0x0000012D0CEF5AC8>
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks conv2d DEBUG input_tensor: Reshape FLOAT32(<tile.Value FloorDiv FLOAT64()>, 64, 64, 64), filters: 3, kernel_size: 5, strides: (1, 1), padding: same, kwargs: {'activation': 'sigmoid', 'name': 'face_out'})
05/22/2023 13:03:21 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x0000012D0CF02F88>
05/22/2023 13:03:21 MainProcess _training_0 _base add_network DEBUG network_type: 'decoder', side: 'b', network: '<keras.engine.training.Model object at 0x0000012D0CF0E0C8>', is_output: True
05/22/2023 13:03:21 MainProcess _training_0 _base name DEBUG model name: 'original'
05/22/2023 13:03:21 MainProcess _training_0 _base add_network DEBUG name: 'decoder_b', filename: 'original_decoder_B.h5'
05/22/2023 13:03:21 MainProcess _training_0 _base __init__ DEBUG Initializing NNMeta: (filename: 'C:\Users\pfftdammitchris\Desktop\faceswap\models\bigie-2\original_decoder_B.h5', network_type: 'decoder', side: 'b', network: <keras.engine.training.Model object at 0x0000012D0CF0E0C8>, is_output: True
05/22/2023 13:03:22 MainProcess _training_0 _base __init__ DEBUG Initialized NNMeta
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks conv DEBUG input_tensor: input_3 Placeholder FLOAT32(<tile.Value SymbolicDim UINT64()>, 64, 64, 3), filters: 128, kernel_size: 5, strides: 2, use_instance_norm: False, kwargs: {})
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks _get_name DEBUG Generating block name: conv_(<tile.Value SymbolicDim UINT64()>, 64, 64, 3)_0
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks conv2d DEBUG input_tensor: input_3 Placeholder FLOAT32(<tile.Value SymbolicDim UINT64()>, 64, 64, 3), filters: 128, kernel_size: 5, strides: 2, padding: same, kwargs: {'name': 'conv_(<tile.Value SymbolicDim UINT64()>, 64, 64, 3)_0_conv2d'})
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x0000012D0CF21888>
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks conv DEBUG input_tensor: Relu FLOAT32(<tile.Value SymbolicDim UINT64()>, 32, 32, 128), filters: 256, kernel_size: 5, strides: 2, use_instance_norm: False, kwargs: {})
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks _get_name DEBUG Generating block name: conv_(<tile.Value SymbolicDim UINT64()>, 32, 32, 128)_0
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks conv2d DEBUG input_tensor: Relu FLOAT32(<tile.Value SymbolicDim UINT64()>, 32, 32, 128), filters: 256, kernel_size: 5, strides: 2, padding: same, kwargs: {'name': 'conv_(<tile.Value SymbolicDim UINT64()>, 32, 32, 128)_0_conv2d'})
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x0000012D0CF2E608>
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks conv DEBUG input_tensor: Relu FLOAT32(<tile.Value SymbolicDim UINT64()>, 16, 16, 256), filters: 512, kernel_size: 5, strides: 2, use_instance_norm: False, kwargs: {})
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks _get_name DEBUG Generating block name: conv_(<tile.Value SymbolicDim UINT64()>, 16, 16, 256)_0
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks conv2d DEBUG input_tensor: Relu FLOAT32(<tile.Value SymbolicDim UINT64()>, 16, 16, 256), filters: 512, kernel_size: 5, strides: 2, padding: same, kwargs: {'name': 'conv_(<tile.Value SymbolicDim UINT64()>, 16, 16, 256)_0_conv2d'})
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x0000012D0CFB4E88>
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks conv DEBUG input_tensor: Relu FLOAT32(<tile.Value SymbolicDim UINT64()>, 8, 8, 512), filters: 1024, kernel_size: 5, strides: 2, use_instance_norm: False, kwargs: {})
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks _get_name DEBUG Generating block name: conv_(<tile.Value SymbolicDim UINT64()>, 8, 8, 512)_0
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks conv2d DEBUG input_tensor: Relu FLOAT32(<tile.Value SymbolicDim UINT64()>, 8, 8, 512), filters: 1024, kernel_size: 5, strides: 2, padding: same, kwargs: {'name': 'conv_(<tile.Value SymbolicDim UINT64()>, 8, 8, 512)_0_conv2d'})
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x0000012D0CFC0A88>
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks upscale DEBUG input_tensor: Reshape FLOAT32(<tile.Value SymbolicDim UINT64()>, 4, 4, 1024), filters: 512, kernel_size: 3, use_instance_norm: False, kwargs: {})
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks _get_name DEBUG Generating block name: upscale_(<tile.Value SymbolicDim UINT64()>, 4, 4, 1024)_0
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Set default kernel_initializer to: <keras.initializers.VarianceScaling object at 0x0000012D0CFDF048>
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks conv2d DEBUG input_tensor: Reshape FLOAT32(<tile.Value SymbolicDim UINT64()>, 4, 4, 1024), filters: 2048, kernel_size: 3, strides: (1, 1), padding: same, kwargs: {'name': 'upscale_(<tile.Value SymbolicDim UINT64()>, 4, 4, 1024)_0_conv2d', 'kernel_initializer': <keras.initializers.VarianceScaling object at 0x0000012D0CFDF048>})
05/22/2023 13:03:22 MainProcess _training_0 nn_blocks _set_default_initializer DEBUG Using model specified initializer: <keras.initializers.VarianceScaling object at 0x0000012D0CFDF048>
05/22/2023 13:03:22 MainProcess _training_0 _base add_network DEBUG network_type: 'encoder', side: 'None', network: '<keras.engine.training.Model object at 0x0000012D0CFCFC48>', is_output: False
05/22/2023 13:03:22 MainProcess _training_0 _base name DEBUG model name: 'original'
05/22/2023 13:03:22 MainProcess _training_0 _base add_network DEBUG name: 'encoder', filename: 'original_encoder.h5'
05/22/2023 13:03:22 MainProcess _training_0 _base __init__ DEBUG Initializing NNMeta: (filename: 'C:\Users\pfftdammitchris\Desktop\faceswap\models\bigie-2\original_encoder.h5', network_type: 'encoder', side: 'None', network: <keras.engine.training.Model object at 0x0000012D0CFCFC48>, is_output: False
05/22/2023 13:03:22 MainProcess _training_0 _base __init__ DEBUG Initialized NNMeta
05/22/2023 13:03:22 MainProcess _training_0 original add_networks DEBUG Added networks
05/22/2023 13:03:22 MainProcess _training_0 _base load_models DEBUG Load model: (swapped: False)
05/22/2023 13:03:22 MainProcess _training_0 _base models_exist DEBUG Pre-existing models exist: True
05/22/2023 13:03:22 MainProcess _training_0 _base models_exist DEBUG Pre-existing models exist: True
05/22/2023 13:03:22 MainProcess _training_0 _base map_models DEBUG Map models: (swapped: False)
05/22/2023 13:03:22 MainProcess _training_0 _base map_models DEBUG Mapped models: (models_map: {'a': {'decoder': 'C:\\Users\\pfftdammitchris\\Desktop\\faceswap\\models\\bigie-2\\original_decoder_A.h5'}, 'b': {'decoder': 'C:\\Users\\pfftdammitchris\\Desktop\\faceswap\\models\\bigie-2\\original_decoder_B.h5'}})
05/22/2023 13:03:22 MainProcess _training_0 _base load DEBUG Loading model: 'C:\Users\pfftdammitchris\Desktop\faceswap\models\bigie-2\original_decoder_A.h5'
05/22/2023 13:03:22 MainProcess _training_0 attrs __getitem__ DEBUG Creating converter from 3 to 5
05/22/2023 13:03:22 MainProcess _training_0 multithreading run DEBUG Error in thread (_training_0): 'str' object has no attribute 'decode'
05/22/2023 13:03:22 MainProcess MainThread train _monitor DEBUG Thread error detected
05/22/2023 13:03:22 MainProcess MainThread train _monitor DEBUG Closed Monitor
05/22/2023 13:03:22 MainProcess MainThread train _end_thread DEBUG Ending Training thread
05/22/2023 13:03:22 MainProcess MainThread train _end_thread CRITICAL Error caught! Exiting...
05/22/2023 13:03:22 MainProcess MainThread multithreading join DEBUG Joining Threads: '_training'
05/22/2023 13:03:22 MainProcess MainThread multithreading join DEBUG Joining Thread: '_training_0'
05/22/2023 13:03:22 MainProcess MainThread multithreading join ERROR Caught exception in thread: '_training_0'
Traceback (most recent call last):
File "C:\Users\pfftdammitchris\faceswap\lib\cli\launcher.py", line 155, in execute_script
process.process()
File "C:\Users\pfftdammitchris\faceswap\scripts\train.py", line 161, in process
self._end_thread(thread, err)
File "C:\Users\pfftdammitchris\faceswap\scripts\train.py", line 201, in _end_thread
thread.join()
File "C:\Users\pfftdammitchris\faceswap\lib\multithreading.py", line 121, in join
raise thread.err[1].with_traceback(thread.err[2])
File "C:\Users\pfftdammitchris\faceswap\lib\multithreading.py", line 37, in run
self._target(*self._args, **self._kwargs)
File "C:\Users\pfftdammitchris\faceswap\scripts\train.py", line 226, in _training
raise err
File "C:\Users\pfftdammitchris\faceswap\scripts\train.py", line 214, in _training
model = self._load_model()
File "C:\Users\pfftdammitchris\faceswap\scripts\train.py", line 255, in _load_model
predict=False)
File "C:\Users\pfftdammitchris\faceswap\plugins\train\model\original.py", line 25, in __init__
super().__init__(*args, **kwargs)
File "C:\Users\pfftdammitchris\faceswap\plugins\train\model\_base.py", line 125, in __init__
self.build()
File "C:\Users\pfftdammitchris\faceswap\plugins\train\model\_base.py", line 244, in build
self.load_models(swapped=False)
File "C:\Users\pfftdammitchris\faceswap\plugins\train\model\_base.py", line 456, in load_models
is_loaded = network.load(fullpath=model_mapping[network.side][network.type])
File "C:\Users\pfftdammitchris\faceswap\plugins\train\model\_base.py", line 834, in load
network = load_model(self.filename, custom_objects=get_custom_objects())
File "C:\Users\pfftdammitchris\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\saving.py", line 419, in load_model
model = _deserialize_model(f, custom_objects, compile)
File "C:\Users\pfftdammitchris\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\saving.py", line 224, in _deserialize_model
model_config = json.loads(model_config.decode('utf-8'))
AttributeError: 'str' object has no attribute 'decode'
============ System Information ============
encoding: cp1252
git_branch: r1.0
git_commits: a4ccfc6 GUI - Remove Switch Branch option Installers - Pin to r1.0
gpu_cuda: No global version found. Check Conda packages for Conda Cuda
gpu_cudnn: No global version found. Check Conda packages for Conda cuDNN
gpu_devices: GPU_0: NVIDIA Corporation - NVIDIA GeForce RTX 3050 Laptop GPU (experimental), GPU_1: NVIDIA Corporation - NVIDIA GeForce RTX 3050 Laptop GPU (supported)
gpu_devices_active: GPU_0, GPU_1
gpu_driver: ['516.40', '516.40']
gpu_vram: GPU_0: 4095MB, GPU_1: 4095MB
os_machine: AMD64
os_platform: Windows-10-10.0.22621-SP0
os_release: 10
py_command: C:\Users\pfftdammitchris\faceswap\faceswap.py train -A C:/Users/pfftdammitchris/Desktop/faceswap/input-A/7-faces -ala C:/Users/pfftdammitchris/Desktop/faceswap/input-A/7_alignments.fsa -B C:/Users/pfftdammitchris/Desktop/faceswap/output-B -alb C:/Users/pfftdammitchris/Desktop/faceswap/output-B/alignments.fsa -m C:/Users/pfftdammitchris/Desktop/faceswap/models/bigie-2 -t original -bs 64 -it 1000000 -s 100 -ss 25000 -ps 50 -L DEBUG -gui
py_conda_version: conda 23.3.1
py_implementation: CPython
py_version: 3.7.16
py_virtual_env: True
sys_cores: 16
sys_processor: AMD64 Family 25 Model 68 Stepping 1, AuthenticAMD
sys_ram: Total: 15629MB, Available: 701MB, Used: 14927MB, Free: 701MB
=============== Pip Packages ===============
absl-py @ file:///opt/conda/conda-bld/absl-py_1639803114343/work
aiohttp @ file:///C:/b/abs_c4zmy2l696/croot/aiohttp_1670009573673/work
aiosignal @ file:///tmp/build/80754af9/aiosignal_1637843061372/work
astor==0.8.1
async-timeout @ file:///C:/b/abs_43ozhz2a8g/croots/recipe/async-timeout_1664876362767/work
asynctest==0.13.0
attrs @ file:///C:/b/abs_09s3y775ra/croot/attrs_1668696195628/work
blinker==1.4
brotlipy==0.7.0
cachetools @ file:///tmp/build/80754af9/cachetools_1619597386817/work
certifi @ file:///C:/b/abs_85o_6fm0se/croot/certifi_1671487778835/work/certifi
cffi @ file:///C:/b/abs_49n3v2hyhr/croot/cffi_1670423218144/work
charset-normalizer @ file:///tmp/build/80754af9/charset-normalizer_1630003229654/work
click @ file:///C:/ci/click_1646038601470/work
cloudpickle @ file:///tmp/build/80754af9/cloudpickle_1632508026186/work
colorama @ file:///C:/b/abs_a9ozq0l032/croot/colorama_1672387194846/work
cryptography @ file:///C:/b/abs_8ecplyc3n2/croot/cryptography_1677533105000/work
cycler @ file:///tmp/build/80754af9/cycler_1637851556182/work
cytoolz @ file:///C:/b/abs_61m9vzb4qh/croot/cytoolz_1667465938275/work
dask==2021.10.0
enum34==1.1.10
fastcluster==1.1.26
ffmpy==0.2.3
flit_core @ file:///opt/conda/conda-bld/flit-core_1644941570762/work/source/flit_core
fonttools==4.25.0
frozenlist @ file:///C:/b/abs_2bb5uzghsi/croot/frozenlist_1670004511812/work
fsspec @ file:///C:/b/abs_5bjz6v0w_f/croot/fsspec_1670336608940/work
gast==0.2.2
google-auth @ file:///opt/conda/conda-bld/google-auth_1646735974934/work
google-auth-oauthlib @ file:///tmp/build/80754af9/google-auth-oauthlib_1617120569401/work
google-pasta @ file:///Users/ktietz/demo/mc3/conda-bld/google-pasta_1630577991354/work
grpcio @ file:///C:/ci/grpcio_1637590993074/work
h5py @ file:///C:/ci/h5py_1659089886851/work
idna @ file:///C:/b/abs_bdhbebrioa/croot/idna_1666125572046/work
imagecodecs @ file:///C:/b/abs_f0cr12h73p/croot/imagecodecs_1677576746499/work
imageio @ file:///C:/Windows/TEMP/abs_24c1b783-7540-4ca9-a1b1-0e8aa8e6ae64hb79ssux/croots/recipe/imageio_1658785038775/work
imageio-ffmpeg @ file:///home/conda/feedstock_root/build_artifacts/imageio-ffmpeg_1673483481485/work
importlib-metadata @ file:///C:/ci/importlib-metadata_1648562631189/work
joblib @ file:///C:/b/abs_e60_bwl1v6/croot/joblib_1666298845728/work
Keras==2.2.4
Keras-Applications @ file:///tmp/build/80754af9/keras-applications_1594366238411/work
Keras-Preprocessing @ file:///tmp/build/80754af9/keras-preprocessing_1612283640596/work
kiwisolver @ file:///C:/ci/kiwisolver_1644944417636/work
locket @ file:///C:/ci/locket_1652885902808/work
Markdown @ file:///C:/b/abs_98lv_ucina/croot/markdown_1671541919225/work
matplotlib @ file:///C:/b/abs_ae02atcfur/croot/matplotlib-suite_1667356722968/work
mkl-fft==1.3.1
mkl-random @ file:///C:/ci/mkl_random_1626186163140/work
mkl-service==2.4.0
multidict @ file:///C:/b/abs_6cx_8w3cv2/croot/multidict_1665674238352/work
munkres==1.1.4
networkx @ file:///tmp/build/80754af9/networkx_1633639043937/work
numpy @ file:///C:/ci/numpy_and_numpy_base_1653574840943/work
nvidia-ml-py3 @ git+https://github.com/deepfakes/nvidia-ml-py3.git@6fc29ac84b32bad877f078cb4a777c1548a00bf6
oauthlib @ file:///C:/b/abs_2eoymqc2ow/croot/oauthlib_1665490906043/work
opencv-python==4.7.0.72
opt-einsum @ file:///tmp/build/80754af9/opt_einsum_1621500238896/work
packaging @ file:///C:/b/abs_cfsup8ur87/croot/packaging_1671697442297/work
partd @ file:///opt/conda/conda-bld/partd_1647245470509/work
Pillow==9.4.0
plaidml==0.6.4
plaidml-keras==0.6.4
ply==3.11
protobuf==3.20.3
psutil @ file:///C:/Windows/Temp/abs_b2c2fd7f-9fd5-4756-95ea-8aed74d0039flsd9qufz/croots/recipe/psutil_1656431277748/work
pyasn1 @ file:///Users/ktietz/demo/mc3/conda-bld/pyasn1_1629708007385/work
pyasn1-modules==0.2.8
pycparser @ file:///tmp/build/80754af9/pycparser_1636541352034/work
PyJWT @ file:///C:/ci/pyjwt_1657529476747/work
pyOpenSSL @ file:///C:/b/abs_552w85x1jz/croot/pyopenssl_1677607703691/work
pyparsing @ file:///C:/Users/BUILDE~1/AppData/Local/Temp/abs_7f_7lba6rl/croots/recipe/pyparsing_1661452540662/work
PyQt5==5.15.7
PyQt5-sip @ file:///C:/Windows/Temp/abs_d7gmd2jg8i/croots/recipe/pyqt-split_1659273064801/work/pyqt_sip
PySocks @ file:///C:/ci/pysocks_1594394709107/work
python-dateutil @ file:///tmp/build/80754af9/python-dateutil_1626374649649/work
PyWavelets @ file:///C:/ci/pywavelets_1648728036674/work
pywin32==305.1
PyYAML==6.0
requests @ file:///C:/ci/requests_1657735288441/work
requests-oauthlib==1.3.0
rsa @ file:///tmp/build/80754af9/rsa_1614366226499/work
scikit-image @ file:///C:/b/abs_63r0vmx78u/croot/scikit-image_1669241746873/work
scikit-learn @ file:///C:/ci/scikit-learn_1642599122269/work
scipy @ file:///C:/ci/scipy_1661333074914/work
sip @ file:///C:/Windows/Temp/abs_b8fxd17m2u/croots/recipe/sip_1659012372737/work
six @ file:///tmp/build/80754af9/six_1644875935023/work
tensorboard @ file:///C:/tf/b/tensorboard_1660161540402/work/tensorboard-2.8.0-py3-none-any.whl
tensorboard-data-server @ file:///C:/b/abs_2fhvpo862s/croot/tensorboard-data-server_1670853600144/work/tensorboard_data_server-0.6.1-py3-none-any.whl
tensorboard-plugin-wit @ file:///C:/tf/b/tensorboard-plugin-wit_1660162132996/work/tensorboard_plugin_wit-1.8.1-py3-none-any.whl
tensorflow==1.15.0
tensorflow-estimator @ file:///home/builder/adipietro/tf/tensorflow-estimator_1630508970172/work/tensorflow_estimator-2.6.0-py2.py3-none-any.whl
termcolor==1.1.0
threadpoolctl @ file:///Users/ktietz/demo/mc3/conda-bld/threadpoolctl_1629802263681/work
tifffile @ file:///tmp/build/80754af9/tifffile_1627275862826/work
toml @ file:///tmp/build/80754af9/toml_1616166611790/work
toolz @ file:///C:/b/abs_cfvk6rc40d/croot/toolz_1667464080130/work
toposort==1.5
tornado @ file:///C:/ci/tornado_1662476933490/work
tqdm @ file:///C:/b/abs_0axbz66qik/croots/recipe/tqdm_1664392691071/work
typing_extensions @ file:///C:/b/abs_89eui86zuq/croot/typing_extensions_1669923792806/work
urllib3 @ file:///C:/b/abs_9bcwxczrvm/croot/urllib3_1673575521331/work
Werkzeug==0.16.1
win-inet-pton @ file:///C:/ci/win_inet_pton_1605306165655/work
wincertstore==0.2
wrapt @ file:///C:/Windows/Temp/abs_7c3dd407-1390-477a-b542-fd15df6a24085_diwiza/croots/recipe/wrapt_1657814452175/work
yarl @ file:///C:/Users/BUILDE~1/AppData/Local/Temp/abs_e5nlunspj6/croots/recipe/yarl_1661437086516/work
zipp @ file:///C:/b/abs_b9jfdr908q/croot/zipp_1672387552360/work
============== Conda Packages ==============
# packages in environment at C:\Users\pfftdammitchris\MiniConda3\envs\faceswap:
#
# Name Version Build Channel
_tflow_select 2.2.0 eigen
absl-py 0.15.0 pyhd3eb1b0_0
aiohttp 3.8.3 py37h2bbff1b_0
aiosignal 1.2.0 pyhd3eb1b0_0
astor 0.8.1 py37haa95532_0
async-timeout 4.0.2 py37haa95532_0
asynctest 0.13.0 py_0
attrs 22.1.0 py37haa95532_0
blas 1.0 mkl
blinker 1.4 py37haa95532_0
blosc 1.21.3 h6c2663c_0
brotli 1.0.9 h2bbff1b_7
brotli-bin 1.0.9 h2bbff1b_7
brotlipy 0.7.0 py37h2bbff1b_1003
bzip2 1.0.8 he774522_0
ca-certificates 2023.01.10 haa95532_0
cachetools 4.2.2 pyhd3eb1b0_0
certifi 2022.12.7 py37haa95532_0
cffi 1.15.1 py37h2bbff1b_3
cfitsio 3.470 h2bbff1b_7
charls 2.2.0 h6c2663c_0
charset-normalizer 2.0.4 pyhd3eb1b0_0
click 8.0.4 py37haa95532_0
cloudpickle 2.0.0 pyhd3eb1b0_0
colorama 0.4.6 py37haa95532_0
cryptography 39.0.1 py37h21b164f_0
cycler 0.11.0 pyhd3eb1b0_0
cytoolz 0.12.0 py37h2bbff1b_0
dask-core 2021.10.0 pyhd3eb1b0_0
enum34 1.1.10 pypi_0 pypi
fastcluster 1.1.26 py37h9386db6_3 conda-forge
ffmpeg 4.3.1 ha925a31_0 conda-forge
ffmpy 0.2.3 pypi_0 pypi
fftw 3.3.9 h2bbff1b_1
flit-core 3.6.0 pyhd3eb1b0_0
fonttools 4.25.0 pyhd3eb1b0_0
freetype 2.12.1 ha860e81_0
frozenlist 1.3.3 py37h2bbff1b_0
fsspec 2022.11.0 py37haa95532_0
gast 0.2.2 py37_0
giflib 5.2.1 h8cc25b3_3
git 2.34.1 haa95532_0
glib 2.69.1 h5dc1a3c_2
google-auth 2.6.0 pyhd3eb1b0_0
google-auth-oauthlib 0.4.4 pyhd3eb1b0_0
google-pasta 0.2.0 pyhd3eb1b0_0
grpcio 1.42.0 py37hc60d5dd_0
gst-plugins-base 1.18.5 h9e645db_0
gstreamer 1.18.5 hd78058f_0
h5py 3.7.0 py37h3de5c98_0
hdf5 1.10.6 h1756f20_1
icc_rt 2022.1.0 h6049295_2
icu 58.2 ha925a31_3
idna 3.4 py37haa95532_0
imagecodecs 2021.8.26 py37h319e4f4_2
imageio 2.19.3 py37haa95532_0
imageio-ffmpeg 0.4.8 pyhd8ed1ab_0 conda-forge
importlib-metadata 4.11.3 py37haa95532_0
intel-openmp 2021.4.0 haa95532_3556
joblib 1.1.1 py37haa95532_0
jpeg 9e h2bbff1b_1
jxrlib 1.1 he774522_2
keras 2.2.4 0
keras-applications 1.0.8 py_1
keras-base 2.2.4 py37_0
keras-preprocessing 1.1.2 pyhd3eb1b0_0
kiwisolver 1.3.2 py37hd77b12b_0
krb5 1.19.4 h5b6d351_0
lcms2 2.12 h83e58a3_0
lerc 3.0 hd77b12b_0
libaec 1.0.4 h33f27b4_1
libbrotlicommon 1.0.9 h2bbff1b_7
libbrotlidec 1.0.9 h2bbff1b_7
libbrotlienc 1.0.9 h2bbff1b_7
libclang 14.0.6 default_hb5a9fac_1
libclang13 14.0.6 default_h8e68704_1
libdeflate 1.17 h2bbff1b_0
libffi 3.4.4 hd77b12b_0
libiconv 1.16 h2bbff1b_2
libogg 1.3.5 h2bbff1b_1
libpng 1.6.39 h8cc25b3_0
libprotobuf 3.20.3 h23ce68f_0
libtiff 4.5.0 h6c2663c_2
libvorbis 1.3.7 he774522_0
libwebp 1.2.4 hbc33d0d_1
libwebp-base 1.2.4 h2bbff1b_1
libxml2 2.10.3 h0ad7f3c_0
libxslt 1.1.37 h2bbff1b_0
libzopfli 1.0.3 ha925a31_0
locket 1.0.0 py37haa95532_0
lz4-c 1.9.4 h2bbff1b_0
markdown 3.4.1 py37haa95532_0
matplotlib 3.5.3 py37haa95532_0
matplotlib-base 3.5.3 py37hd77b12b_0
mkl 2021.4.0 haa95532_640
mkl-service 2.4.0 py37h2bbff1b_0
mkl_fft 1.3.1 py37h277e83a_0
mkl_random 1.2.2 py37hf11a4ad_0
multidict 6.0.2 py37h2bbff1b_0
munkres 1.1.4 py_0
networkx 2.6.3 pyhd3eb1b0_0
numpy 1.21.5 py37h7a0a035_3
numpy-base 1.21.5 py37hca35cd5_3
nvidia-ml-py3 7.352.1 pypi_0 pypi
oauthlib 3.2.1 py37haa95532_0
opencv-python 4.7.0.72 pypi_0 pypi
openjpeg 2.4.0 h4fc8c34_0
openssl 1.1.1t h2bbff1b_0
opt_einsum 3.3.0 pyhd3eb1b0_1
packaging 22.0 py37haa95532_0
partd 1.2.0 pyhd3eb1b0_1
pathlib 1.0.1 py37_2
pcre 8.45 hd77b12b_0
pillow 9.4.0 py37hd77b12b_0
pip 22.3.1 py37haa95532_0
plaidml 0.6.4 pypi_0 pypi
plaidml-keras 0.6.4 pypi_0 pypi
ply 3.11 py37_0
protobuf 3.20.3 py37hd77b12b_0
psutil 5.9.0 py37h2bbff1b_0
pyasn1 0.4.8 pyhd3eb1b0_0
pyasn1-modules 0.2.8 py_0
pycparser 2.21 pyhd3eb1b0_0
pyjwt 2.4.0 py37haa95532_0
pyopenssl 23.0.0 py37haa95532_0
pyparsing 3.0.9 py37haa95532_0
pyqt 5.15.7 py37hd77b12b_0
pyqt5-sip 12.11.0 py37hd77b12b_0
pysocks 1.7.1 py37_1
python 3.7.16 h6244533_0
python-dateutil 2.8.2 pyhd3eb1b0_0
python_abi 3.7 2_cp37m conda-forge
pywavelets 1.3.0 py37h2bbff1b_0
pywin32 305 py37h2bbff1b_0
pyyaml 6.0 py37h2bbff1b_1
qt-main 5.15.2 he8e5bd7_8
qt-webengine 5.15.9 hb9a9bb5_5
qtwebkit 5.212 h2bbfb41_5
requests 2.28.1 py37haa95532_0
requests-oauthlib 1.3.0 py_0
rsa 4.7.2 pyhd3eb1b0_1
scikit-image 0.19.3 py37hd77b12b_1
scikit-learn 1.0.2 py37hf11a4ad_1
scipy 1.7.3 py37h7a0a035_2
setuptools 65.6.3 py37haa95532_0
sip 6.6.2 py37hd77b12b_0
six 1.16.0 pyhd3eb1b0_1
snappy 1.1.9 h6c2663c_0
sqlite 3.41.2 h2bbff1b_0
tensorboard 2.8.0 py37haa95532_0
tensorboard-data-server 0.6.1 py37haa95532_0
tensorboard-plugin-wit 1.8.1 py37haa95532_0
tensorflow 1.15.0 eigen_py37h9f89a44_0
tensorflow-base 1.15.0 eigen_py37h07d2309_0
tensorflow-estimator 2.6.0 pyh7b7c402_0
termcolor 1.1.0 py37haa95532_1
threadpoolctl 2.2.0 pyh0d69192_0
tifffile 2021.7.2 pyhd3eb1b0_2
tk 8.6.12 h2bbff1b_0
toml 0.10.2 pyhd3eb1b0_0
toolz 0.12.0 py37haa95532_0
toposort 1.5 py_3 conda-forge
tornado 6.2 py37h2bbff1b_0
tqdm 4.64.1 py37haa95532_0
typing-extensions 4.4.0 py37haa95532_0
typing_extensions 4.4.0 py37haa95532_0
urllib3 1.26.14 py37haa95532_0
vc 14.2 h21ff451_1
vs2015_runtime 14.27.29016 h5e58377_2
werkzeug 0.16.1 py_0
wheel 0.38.4 py37haa95532_0
win_inet_pton 1.1.0 py37haa95532_0
wincertstore 0.2 py37haa95532_2
wrapt 1.14.1 py37h2bbff1b_0
xz 5.4.2 h8cc25b3_0
yaml 0.2.5 he774522_0
yarl 1.8.1 py37h2bbff1b_0
zfp 0.5.5 hd77b12b_6
zipp 3.11.0 py37haa95532_0
zlib 1.2.13 h8cc25b3_0
zstd 1.5.5 hd43e919_0
=============== State File =================
{
"name": "original",
"sessions": {
"1": {
"timestamp": 1684731234.8941696,
"no_logs": false,
"pingpong": false,
"loss_names": {
"a": [
"face_loss"
],
"b": [
"face_loss"
]
},
"batchsize": 64,
"iterations": 23677,
"config": {
"learning_rate": 5e-05
}
}
},
"lowest_avg_loss": {
"a": 0.03764933113008737,
"b": 0.03583359196782112
},
"iterations": 23677,
"inputs": {
"face_in": [
64,
64,
3
]
},
"training_size": 512,
"config": {
"coverage": 68.75,
"mask_type": null,
"mask_blur_kernel": 3,
"mask_threshold": 4,
"learn_mask": false,
"icnr_init": false,
"conv_aware_init": false,
"reflect_padding": false,
"penalized_mask_loss": true,
"loss_function": "mae",
"learning_rate": 5e-05,
"lowmem": false
}
}
================= Configs ==================
--------- .faceswap ---------
backend: amd
--------- convert.ini ---------
[color.color_transfer]
clip: True
preserve_paper: True
[color.manual_balance]
colorspace: HSV
balance_1: 0.0
balance_2: 0.0
balance_3: 0.0
contrast: 0.0
brightness: 0.0
[color.match_hist]
threshold: 99.0
[mask.box_blend]
type: gaussian
distance: 11.0
radius: 5.0
passes: 1
[mask.mask_blend]
type: normalized
kernel_size: 3
passes: 4
threshold: 4
erosion: 0.0
[scaling.sharpen]
method: unsharp_mask
amount: 150
radius: 0.3
threshold: 5.0
[writer.ffmpeg]
container: mp4
codec: libx264
crf: 23
preset: medium
tune: none
profile: auto
level: auto
skip_mux: False
[writer.gif]
fps: 25
loop: 0
palettesize: 256
subrectangles: False
[writer.opencv]
format: png
draw_transparent: False
jpg_quality: 75
png_compress_level: 3
[writer.pillow]
format: png
draw_transparent: False
optimize: False
gif_interlace: True
jpg_quality: 75
png_compress_level: 3
tif_compression: tiff_deflate
--------- extract.ini ---------
[global]
allow_growth: False
[align.fan]
batch-size: 12
[detect.cv2_dnn]
confidence: 50
[detect.mtcnn]
minsize: 20
threshold_1: 0.6
threshold_2: 0.7
threshold_3: 0.7
scalefactor: 0.709
batch-size: 8
[detect.s3fd]
confidence: 70
batch-size: 4
[mask.unet_dfl]
batch-size: 8
[mask.vgg_clear]
batch-size: 6
[mask.vgg_obstructed]
batch-size: 2
--------- gui.ini ---------
[global]
fullscreen: False
tab: extract
options_panel_width: 30
console_panel_height: 20
icon_size: 14
font: default
font_size: 9
autosave_last_session: prompt
timeout: 120
auto_load_model_stats: True
--------- train.ini ---------
[global]
coverage: 68.75
mask_type: none
mask_blur_kernel: 3
mask_threshold: 4
learn_mask: False
icnr_init: False
conv_aware_init: False
reflect_padding: False
penalized_mask_loss: True
loss_function: mae
learning_rate: 5e-05
[model.dfl_h128]
lowmem: False
[model.dfl_sae]
input_size: 128
clipnorm: True
architecture: df
autoencoder_dims: 0
encoder_dims: 42
decoder_dims: 21
multiscale_decoder: False
[model.dlight]
features: best
details: good
output_size: 256
[model.original]
lowmem: False
[model.realface]
input_size: 64
output_size: 128
dense_nodes: 1536
complexity_encoder: 128
complexity_decoder: 512
[model.unbalanced]
input_size: 128
lowmem: False
clipnorm: True
nodes: 1024
complexity_encoder: 128
complexity_decoder_a: 384
complexity_decoder_b: 512
[model.villain]
lowmem: False
[trainer.original]
preview_images: 14
zoom_amount: 5
rotation_range: 10
shift_range: 5
flip_chance: 50
color_lightness: 30
color_ab: 8
color_clahe_chance: 50
color_clahe_max_size: 4