Training error: Profiling failure on CUDNN engine 1: RESOURCE_EXHAUSTED
Posted: Sat Jul 29, 2023 10:11 am
Code: Select all
07/29/2023 17:54:59 MainProcess _training multithreading start DEBUG Started all threads '_run_0': 1
07/29/2023 17:54:59 MainProcess _training _base _set_preview_feed DEBUG Setting preview feed: (side: 'a')
07/29/2023 17:54:59 MainProcess _training _base _load_generator DEBUG Loading generator, side: a, is_display: True, batch_size: 14
07/29/2023 17:54:59 MainProcess _training generator __init__ DEBUG Initializing PreviewDataGenerator: (model: original, side: a, images: 2936 , batch_size: 14, config: {'centering': 'face', 'coverage': 87.5, 'icnr_init': False, 'conv_aware_init': False, 'optimizer': 'adam', 'learning_rate': 5e-05, 'epsilon_exponent': -7, 'save_optimizer': 'exit', 'autoclip': False, 'reflect_padding': False, 'allow_growth': False, 'mixed_precision': False, 'nan_protection': True, 'convert_batchsize': 16, 'loss_function': 'ssim', 'loss_function_2': 'mse', 'loss_weight_2': 100, 'loss_function_3': None, 'loss_weight_3': 0, 'loss_function_4': None, 'loss_weight_4': 0, 'mask_loss_function': 'mse', 'eye_multiplier': 3, 'mouth_multiplier': 2, 'penalized_mask_loss': True, 'mask_type': 'extended', 'mask_blur_kernel': 3, 'mask_threshold': 4, 'learn_mask': False, 'preview_images': 14, 'mask_opacity': 30, 'mask_color': '#ff0000', '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})
07/29/2023 17:54:59 MainProcess _training generator _get_output_sizes DEBUG side: a, model output shapes: [(None, 64, 64, 3), (None, 64, 64, 3)], output sizes: [64]
07/29/2023 17:54:59 MainProcess _training cache __init__ DEBUG Initializing: RingBuffer (batch_size: 14, image_shape: (64, 64, 6), buffer_size: 2, dtype: uint8
07/29/2023 17:54:59 MainProcess _training cache __init__ DEBUG Initialized: RingBuffer
07/29/2023 17:54:59 MainProcess _training generator __init__ DEBUG Initialized PreviewDataGenerator
07/29/2023 17:54:59 MainProcess _training generator minibatch_ab DEBUG do_shuffle: True
07/29/2023 17:54:59 MainProcess _training multithreading __init__ DEBUG Initializing BackgroundGenerator: (target: '_run_1', thread_count: 1)
07/29/2023 17:54:59 MainProcess _training multithreading __init__ DEBUG Initialized BackgroundGenerator: '_run_1'
07/29/2023 17:54:59 MainProcess _training multithreading start DEBUG Starting thread(s): '_run_1'
07/29/2023 17:54:59 MainProcess _training multithreading start DEBUG Starting thread 1 of 1: '_run_1'
07/29/2023 17:54:59 MainProcess _run_1 generator _minibatch DEBUG Loading minibatch generator: (image_count: 2936, do_shuffle: True)
07/29/2023 17:54:59 MainProcess _training multithreading start DEBUG Started all threads '_run_1': 1
07/29/2023 17:54:59 MainProcess _training _base _set_preview_feed DEBUG Setting preview feed: (side: 'b')
07/29/2023 17:54:59 MainProcess _training _base _load_generator DEBUG Loading generator, side: b, is_display: True, batch_size: 14
07/29/2023 17:54:59 MainProcess _training generator __init__ DEBUG Initializing PreviewDataGenerator: (model: original, side: b, images: 400 , batch_size: 14, config: {'centering': 'face', 'coverage': 87.5, 'icnr_init': False, 'conv_aware_init': False, 'optimizer': 'adam', 'learning_rate': 5e-05, 'epsilon_exponent': -7, 'save_optimizer': 'exit', 'autoclip': False, 'reflect_padding': False, 'allow_growth': False, 'mixed_precision': False, 'nan_protection': True, 'convert_batchsize': 16, 'loss_function': 'ssim', 'loss_function_2': 'mse', 'loss_weight_2': 100, 'loss_function_3': None, 'loss_weight_3': 0, 'loss_function_4': None, 'loss_weight_4': 0, 'mask_loss_function': 'mse', 'eye_multiplier': 3, 'mouth_multiplier': 2, 'penalized_mask_loss': True, 'mask_type': 'extended', 'mask_blur_kernel': 3, 'mask_threshold': 4, 'learn_mask': False, 'preview_images': 14, 'mask_opacity': 30, 'mask_color': '#ff0000', '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})
07/29/2023 17:54:59 MainProcess _training generator _get_output_sizes DEBUG side: b, model output shapes: [(None, 64, 64, 3), (None, 64, 64, 3)], output sizes: [64]
07/29/2023 17:54:59 MainProcess _training cache __init__ DEBUG Initializing: RingBuffer (batch_size: 14, image_shape: (64, 64, 6), buffer_size: 2, dtype: uint8
07/29/2023 17:54:59 MainProcess _training cache __init__ DEBUG Initialized: RingBuffer
07/29/2023 17:54:59 MainProcess _training generator __init__ DEBUG Initialized PreviewDataGenerator
07/29/2023 17:54:59 MainProcess _training generator minibatch_ab DEBUG do_shuffle: True
07/29/2023 17:54:59 MainProcess _training multithreading __init__ DEBUG Initializing BackgroundGenerator: (target: '_run_2', thread_count: 1)
07/29/2023 17:54:59 MainProcess _training multithreading __init__ DEBUG Initialized BackgroundGenerator: '_run_2'
07/29/2023 17:54:59 MainProcess _training multithreading start DEBUG Starting thread(s): '_run_2'
07/29/2023 17:54:59 MainProcess _training multithreading start DEBUG Starting thread 1 of 1: '_run_2'
07/29/2023 17:54:59 MainProcess _run_2 generator _minibatch DEBUG Loading minibatch generator: (image_count: 400, do_shuffle: True)
07/29/2023 17:54:59 MainProcess _training multithreading start DEBUG Started all threads '_run_2': 1
07/29/2023 17:54:59 MainProcess _training _base __init__ DEBUG Initialized _Feeder:
07/29/2023 17:54:59 MainProcess _training _base _set_tensorboard DEBUG Enabling TensorBoard Logging
07/29/2023 17:54:59 MainProcess _training _base _set_tensorboard DEBUG Setting up TensorBoard Logging
07/29/2023 17:54:59 MainProcess _training _base _set_tensorboard VERBOSE Enabled TensorBoard Logging
07/29/2023 17:54:59 MainProcess _training _base __init__ DEBUG Initializing _Samples: model: '<plugins.train.model.original.Model object at 0x000001BA24870190>', coverage_ratio: 0.875, mask_opacity: 30, mask_color: #ff0000)
07/29/2023 17:54:59 MainProcess _training _base __init__ DEBUG Initialized _Samples
07/29/2023 17:54:59 MainProcess _training _base __init__ DEBUG Initializing _Timelapse: model: <plugins.train.model.original.Model object at 0x000001BA24870190>, coverage_ratio: 0.875, image_count: 14, mask_opacity: 30, mask_color: #ff0000, feeder: <plugins.train.trainer._base._Feeder object at 0x000001BA248726B0>, image_paths: 2)
07/29/2023 17:54:59 MainProcess _training _base __init__ DEBUG Initializing _Samples: model: '<plugins.train.model.original.Model object at 0x000001BA24870190>', coverage_ratio: 0.875, mask_opacity: 30, mask_color: #ff0000)
07/29/2023 17:54:59 MainProcess _training _base __init__ DEBUG Initialized _Samples
07/29/2023 17:54:59 MainProcess _training _base __init__ DEBUG Initialized _Timelapse
07/29/2023 17:54:59 MainProcess _training _base __init__ DEBUG Initialized Trainer
07/29/2023 17:54:59 MainProcess _training train _load_trainer DEBUG Loaded Trainer
07/29/2023 17:54:59 MainProcess _training train _run_training_cycle DEBUG Running Training Cycle
07/29/2023 17:54:59 MainProcess _run cache _validate_version DEBUG Setting initial extract version: 2.3
07/29/2023 17:54:59 MainProcess _run_0 cache _validate_version DEBUG Setting initial extract version: 2.3
07/29/2023 17:55:00 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA215F5A50>, weight: 1.0, mask_channel: 3)
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Applying mask from channel 3
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD7A830>, weight: 3.0, mask_channel: 4)
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Applying mask from channel 4
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD79840>, weight: 2.0, mask_channel: 5)
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Applying mask from channel 5
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD79600>, weight: 1.0, mask_channel: 3)
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Applying mask from channel 3
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD7A2C0>, weight: 3.0, mask_channel: 4)
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Applying mask from channel 4
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD79810>, weight: 2.0, mask_channel: 5)
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Applying mask from channel 5
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD79D50>, weight: 1.0, mask_channel: 3)
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Applying mask from channel 3
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD78EE0>, weight: 3.0, mask_channel: 4)
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Applying mask from channel 4
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD79360>, weight: 2.0, mask_channel: 5)
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Applying mask from channel 5
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD791B0>, weight: 1.0, mask_channel: 3)
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Applying mask from channel 3
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD78370>, weight: 3.0, mask_channel: 4)
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Applying mask from channel 4
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD8FD30>, weight: 2.0, mask_channel: 5)
07/29/2023 17:55:01 MainProcess _training api converted_call DEBUG Applying mask from channel 5
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA215F5A50>, weight: 1.0, mask_channel: 3)
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Applying mask from channel 3
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD7A830>, weight: 3.0, mask_channel: 4)
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Applying mask from channel 4
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD79840>, weight: 2.0, mask_channel: 5)
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Applying mask from channel 5
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD79600>, weight: 1.0, mask_channel: 3)
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Applying mask from channel 3
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD7A2C0>, weight: 3.0, mask_channel: 4)
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Applying mask from channel 4
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD79810>, weight: 2.0, mask_channel: 5)
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Applying mask from channel 5
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD79D50>, weight: 1.0, mask_channel: 3)
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Applying mask from channel 3
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD78EE0>, weight: 3.0, mask_channel: 4)
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Applying mask from channel 4
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD79360>, weight: 2.0, mask_channel: 5)
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Applying mask from channel 5
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD791B0>, weight: 1.0, mask_channel: 3)
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Applying mask from channel 3
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD78370>, weight: 3.0, mask_channel: 4)
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Applying mask from channel 4
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Processing loss function: (func: <tensorflow.python.keras.engine.compile_utils.LossesContainer object at 0x000001BA3DD8FD30>, weight: 2.0, mask_channel: 5)
07/29/2023 17:55:02 MainProcess _training api converted_call DEBUG Applying mask from channel 5
07/29/2023 17:55:05 MainProcess _training multithreading run DEBUG Error in thread (_training): Graph execution error:\n\nDetected at node 'gradient_tape/original/encoder/upscale_512_0_conv2d_conv2d/Conv2D_1/Conv2DBackpropInput' defined at (most recent call last):\n File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\threading.py", line 973, in _bootstrap\n self._bootstrap_inner()\n File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\threading.py", line 1016, in _bootstrap_inner\n self.run()\n File "D:\faceswap\lib\multithreading.py", line 100, in run\n self._target(*self._args, **self._kwargs)\n File "D:\faceswap\scripts\train.py", line 261, in _training\n self._run_training_cycle(model, trainer)\n File "D:\faceswap\scripts\train.py", line 349, in _run_training_cycle\n trainer.train_one_step(viewer, timelapse)\n File "D:\faceswap\plugins\train\trainer\_base.py", line 214, in train_one_step\n loss: list[float] = self._model.model.train_on_batch(model_inputs, y=model_targets)\n File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\training.py", line 2381, in train_on_batch\n logs = self.train_function(iterator)\n File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\training.py", line 1160, in train_function\n return step_function(self, iterator)\n File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\training.py", line 1146, in step_function\n outputs = model.distribute_strategy.run(run_step, args=(data,))\n File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\training.py", line 1135, in run_step\n outputs = model.train_step(data)\n File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\training.py", line 997, in train_step\n self.optimizer.minimize(loss, self.trainable_variables, tape=tape)\n File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\optimizers\optimizer_v2\optimizer_v2.py", line 576, in minimize\n grads_and_vars = self._compute_gradients(\n File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\optimizers\optimizer_v2\optimizer_v2.py", line 634, in _compute_gradients\n grads_and_vars = self._get_gradients(\n File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\optimizers\optimizer_v2\optimizer_v2.py", line 510, in _get_gradients\n grads = tape.gradient(loss, var_list, grad_loss)\nNode: 'gradient_tape/original/encoder/upscale_512_0_conv2d_conv2d/Conv2D_1/Conv2DBackpropInput'\nNo algorithm worked! Error messages:\n Profiling failure on CUDNN engine 1: RESOURCE_EXHAUSTED: Out of memory while trying to allocate 17041664 bytes.\n Profiling failure on CUDNN engine 4: RESOURCE_EXHAUSTED: Out of memory while trying to allocate 226496512 bytes.\n Profiling failure on CUDNN engine 5: RESOURCE_EXHAUSTED: Out of memory while trying to allocate 325844992 bytes.\n Profiling failure on CUDNN engine 0: RESOURCE_EXHAUSTED: Out of memory while trying to allocate 16777216 bytes.\n [[{{node gradient_tape/original/encoder/upscale_512_0_conv2d_conv2d/Conv2D_1/Conv2DBackpropInput}}]] [Op:__inference_train_function_7782]
07/29/2023 17:55:05 MainProcess MainThread train _monitor DEBUG Thread error detected
07/29/2023 17:55:05 MainProcess MainThread train _monitor DEBUG Closed Monitor
07/29/2023 17:55:05 MainProcess MainThread train _end_thread DEBUG Ending Training thread
07/29/2023 17:55:05 MainProcess MainThread train _end_thread CRITICAL Error caught! Exiting...
07/29/2023 17:55:05 MainProcess MainThread multithreading join DEBUG Joining Threads: '_training'
07/29/2023 17:55:05 MainProcess MainThread multithreading join DEBUG Joining Thread: '_training'
07/29/2023 17:55:05 MainProcess MainThread multithreading join ERROR Caught exception in thread: '_training'
Traceback (most recent call last):
File "D:\faceswap\lib\cli\launcher.py", line 225, in execute_script
process.process()
File "D:\faceswap\scripts\train.py", line 209, in process
self._end_thread(thread, err)
File "D:\faceswap\scripts\train.py", line 249, in _end_thread
thread.join()
File "D:\faceswap\lib\multithreading.py", line 224, in join
raise thread.err[1].with_traceback(thread.err[2])
File "D:\faceswap\lib\multithreading.py", line 100, in run
self._target(*self._args, **self._kwargs)
File "D:\faceswap\scripts\train.py", line 271, in _training
raise err
File "D:\faceswap\scripts\train.py", line 261, in _training
self._run_training_cycle(model, trainer)
File "D:\faceswap\scripts\train.py", line 349, in _run_training_cycle
trainer.train_one_step(viewer, timelapse)
File "D:\faceswap\plugins\train\trainer\_base.py", line 214, in train_one_step
loss: list[float] = self._model.model.train_on_batch(model_inputs, y=model_targets)
File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\training.py", line 2381, in train_on_batch
logs = self.train_function(iterator)
File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\tensorflow\python\util\traceback_utils.py", line 153, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\tensorflow\python\eager\execute.py", line 54, in quick_execute
tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
tensorflow.python.framework.errors_impl.NotFoundError: Graph execution error:
Detected at node 'gradient_tape/original/encoder/upscale_512_0_conv2d_conv2d/Conv2D_1/Conv2DBackpropInput' defined at (most recent call last):
File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\threading.py", line 973, in _bootstrap
self._bootstrap_inner()
File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\threading.py", line 1016, in _bootstrap_inner
self.run()
File "D:\faceswap\lib\multithreading.py", line 100, in run
self._target(*self._args, **self._kwargs)
File "D:\faceswap\scripts\train.py", line 261, in _training
self._run_training_cycle(model, trainer)
File "D:\faceswap\scripts\train.py", line 349, in _run_training_cycle
trainer.train_one_step(viewer, timelapse)
File "D:\faceswap\plugins\train\trainer\_base.py", line 214, in train_one_step
loss: list[float] = self._model.model.train_on_batch(model_inputs, y=model_targets)
File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\training.py", line 2381, in train_on_batch
logs = self.train_function(iterator)
File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\training.py", line 1160, in train_function
return step_function(self, iterator)
File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\training.py", line 1146, in step_function
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\training.py", line 1135, in run_step
outputs = model.train_step(data)
File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\training.py", line 997, in train_step
self.optimizer.minimize(loss, self.trainable_variables, tape=tape)
File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\optimizers\optimizer_v2\optimizer_v2.py", line 576, in minimize
grads_and_vars = self._compute_gradients(
File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\optimizers\optimizer_v2\optimizer_v2.py", line 634, in _compute_gradients
grads_and_vars = self._get_gradients(
File "C:\Users\Administrator\MiniConda3\envs\faceswap\lib\site-packages\keras\optimizers\optimizer_v2\optimizer_v2.py", line 510, in _get_gradients
grads = tape.gradient(loss, var_list, grad_loss)
Node: 'gradient_tape/original/encoder/upscale_512_0_conv2d_conv2d/Conv2D_1/Conv2DBackpropInput'
No algorithm worked! Error messages:
Profiling failure on CUDNN engine 1: RESOURCE_EXHAUSTED: Out of memory while trying to allocate 17041664 bytes.
Profiling failure on CUDNN engine 4: RESOURCE_EXHAUSTED: Out of memory while trying to allocate 226496512 bytes.
Profiling failure on CUDNN engine 5: RESOURCE_EXHAUSTED: Out of memory while trying to allocate 325844992 bytes.
Profiling failure on CUDNN engine 0: RESOURCE_EXHAUSTED: Out of memory while trying to allocate 16777216 bytes.
[[{{node gradient_tape/original/encoder/upscale_512_0_conv2d_conv2d/Conv2D_1/Conv2DBackpropInput}}]] [Op:__inference_train_function_7782]
============ System Information ============
backend: nvidia
encoding: cp936
git_branch: master
git_commits: 81e3bf5 Merge pull request #1331 from torzdf/macos
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 GeForce GTX 960
gpu_devices_active: GPU_0
gpu_driver: 528.02
gpu_vram: GPU_0: 2048MB (57MB free)
os_machine: AMD64
os_platform: Windows-10-10.0.19044-SP0
os_release: 10
py_command: D:\faceswap\faceswap.py train -A C:/Users/Administrator/Desktop/a -B C:/Users/Administrator/Desktop/b -m C:/Users/Administrator/Desktop/C -t original -bs 4 -it 1000000 -D default -s 250 -ss 25000 -tia C:/Users/Administrator/Desktop/a -tib C:/Users/Administrator/Desktop/b -to C:/Users/Administrator/Desktop/D -L INFO -gui
py_conda_version: conda 23.7.2
py_implementation: CPython
py_version: 3.10.12
py_virtual_env: True
sys_cores: 16
sys_processor: Intel64 Family 6 Model 151 Stepping 2, GenuineIntel
sys_ram: Total: 32609MB, Available: 23124MB, Used: 9484MB, Free: 23124MB
=============== Pip Packages ===============
absl-py==1.4.0
appdirs==1.4.4
astunparse==1.6.3
brotlipy==0.7.0
cachetools==5.3.1
certifi==2023.7.22
cffi @ file:///C:/b/abs_49n3v2hyhr/croot/cffi_1670423218144/work
charset-normalizer @ file:///tmp/build/80754af9/charset-normalizer_1630003229654/work
colorama @ file:///C:/b/abs_a9ozq0l032/croot/colorama_1672387194846/work
contourpy @ file:///C:/b/abs_d5rpy288vc/croots/recipe/contourpy_1663827418189/work
cryptography @ file:///C:/b/abs_13590mi9q9/croot/cryptography_1689373706078/work
cycler @ file:///tmp/build/80754af9/cycler_1637851556182/work
fastcluster @ file:///D:/bld/fastcluster_1667859055985/work
ffmpy @ file:///home/conda/feedstock_root/build_artifacts/ffmpy_1659474992694/work
flatbuffers==23.5.26
fonttools==4.25.0
gast==0.4.0
google-auth==2.22.0
google-auth-oauthlib==0.4.6
google-pasta==0.2.0
grpcio==1.56.2
h5py==3.9.0
idna @ file:///C:/b/abs_bdhbebrioa/croot/idna_1666125572046/work
imageio @ file:///C:/b/abs_27kq2gy1us/croot/imageio_1677879918708/work
imageio-ffmpeg @ file:///home/conda/feedstock_root/build_artifacts/imageio-ffmpeg_1673483481485/work
joblib @ file:///C:/b/abs_1anqjntpan/croot/joblib_1685113317150/work
keras==2.10.0
Keras-Preprocessing==1.1.2
kiwisolver @ file:///C:/b/abs_88mdhvtahm/croot/kiwisolver_1672387921783/work
libclang==16.0.6
Markdown==3.4.4
MarkupSafe==2.1.3
matplotlib @ file:///C:/b/abs_49b2acwxd4/croot/matplotlib-suite_1679593486357/work
mkl-fft==1.3.6
mkl-random @ file:///C:/Users/dev-admin/mkl/mkl_random_1682977971003/work
mkl-service==2.4.0
munkres==1.1.4
numexpr @ file:///C:/b/abs_afm0oewmmt/croot/numexpr_1683221839116/work
numpy @ file:///C:/b/abs_5akk51tu0f/croot/numpy_and_numpy_base_1687466253743/work
nvidia-ml-py @ file:///home/conda/feedstock_root/build_artifacts/nvidia-ml-py_1688681764027/work
oauthlib==3.2.2
opencv-python==4.8.0.74
opt-einsum==3.3.0
packaging @ file:///C:/b/abs_ed_kb9w6g4/croot/packaging_1678965418855/work
Pillow==9.4.0
ply==3.11
pooch @ file:///tmp/build/80754af9/pooch_1623324770023/work
protobuf==3.19.6
psutil @ file:///C:/Windows/Temp/abs_b2c2fd7f-9fd5-4756-95ea-8aed74d0039flsd9qufz/croots/recipe/psutil_1656431277748/work
pyasn1==0.5.0
pyasn1-modules==0.3.0
pycparser @ file:///tmp/build/80754af9/pycparser_1636541352034/work
pyOpenSSL @ file:///C:/b/abs_08f38zyck4/croot/pyopenssl_1690225407403/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_310/pysocks_1642089375450/work
python-dateutil @ file:///tmp/build/80754af9/python-dateutil_1626374649649/work
pywin32==305.1
pywinpty @ file:///C:/ci_310/pywinpty_1644230983541/work/target/wheels/pywinpty-2.0.2-cp310-none-win_amd64.whl
requests @ file:///C:/b/abs_316c2inijk/croot/requests_1690400295842/work
requests-oauthlib==1.3.1
rsa==4.9
scikit-learn @ file:///C:/b/abs_38k7ridbgr/croot/scikit-learn_1684954723009/work
scipy==1.10.1
sip @ file:///C:/Windows/Temp/abs_b8fxd17m2u/croots/recipe/sip_1659012372737/work
six @ file:///tmp/build/80754af9/six_1644875935023/work
tensorboard==2.10.1
tensorboard-data-server==0.6.1
tensorboard-plugin-wit==1.8.1
tensorflow==2.10.1
tensorflow-estimator==2.10.0
tensorflow-io-gcs-filesystem==0.31.0
termcolor==2.3.0
threadpoolctl @ file:///Users/ktietz/demo/mc3/conda-bld/threadpoolctl_1629802263681/work
toml @ file:///tmp/build/80754af9/toml_1616166611790/work
tornado @ file:///C:/ci/tornado_1662476985533/work
tqdm @ file:///C:/b/abs_f76j9hg7pv/croot/tqdm_1679561871187/work
typing_extensions==4.7.1
urllib3 @ file:///C:/b/abs_889_loyqv4/croot/urllib3_1686163174463/work
Werkzeug==2.3.6
win-inet-pton @ file:///C:/ci_310/win_inet_pton_1642658466512/work
wrapt==1.15.0
============== Conda Packages ==============
# packages in environment at C:\Users\Administrator\MiniConda3\envs\faceswap:
#
# Name Version Build Channel
absl-py 1.4.0 pypi_0 pypi
appdirs 1.4.4 pyhd3eb1b0_0
astunparse 1.6.3 pypi_0 pypi
blas 1.0 mkl
brotli 1.0.9 h2bbff1b_7
brotli-bin 1.0.9 h2bbff1b_7
brotlipy 0.7.0 py310h2bbff1b_1002
bzip2 1.0.8 he774522_0
ca-certificates 2023.7.22 h56e8100_0 conda-forge
cachetools 5.3.1 pypi_0 pypi
certifi 2023.7.22 pyhd8ed1ab_0 conda-forge
cffi 1.15.1 py310h2bbff1b_3
charset-normalizer 2.0.4 pyhd3eb1b0_0
colorama 0.4.6 py310haa95532_0
contourpy 1.0.5 py310h59b6b97_0
cryptography 41.0.2 py310h31511bf_0
cudatoolkit 11.8.0 hd77b12b_0
cudnn 8.9.2.26 cuda11_0
cycler 0.11.0 pyhd3eb1b0_0
fastcluster 1.2.6 py310h1c4a608_2 conda-forge
ffmpeg 4.3.1 ha925a31_0 conda-forge
ffmpy 0.3.0 pyhb6f538c_0 conda-forge
flatbuffers 23.5.26 pypi_0 pypi
fonttools 4.25.0 pyhd3eb1b0_0
freetype 2.12.1 ha860e81_0
gast 0.4.0 pypi_0 pypi
giflib 5.2.1 h8cc25b3_3
git 2.40.1 haa95532_1
glib 2.69.1 h5dc1a3c_2
google-auth 2.22.0 pypi_0 pypi
google-auth-oauthlib 0.4.6 pypi_0 pypi
google-pasta 0.2.0 pypi_0 pypi
grpcio 1.56.2 pypi_0 pypi
gst-plugins-base 1.18.5 h9e645db_0
gstreamer 1.18.5 hd78058f_0
h5py 3.9.0 pypi_0 pypi
icc_rt 2022.1.0 h6049295_2
icu 58.2 ha925a31_3
idna 3.4 py310haa95532_0
imageio 2.26.0 py310haa95532_0
imageio-ffmpeg 0.4.8 pyhd8ed1ab_0 conda-forge
intel-openmp 2023.1.0 h59b6b97_46319
joblib 1.2.0 py310haa95532_0
jpeg 9e h2bbff1b_1
keras 2.10.0 pypi_0 pypi
keras-preprocessing 1.1.2 pypi_0 pypi
kiwisolver 1.4.4 py310hd77b12b_0
krb5 1.19.4 h5b6d351_0
lerc 3.0 hd77b12b_0
libbrotlicommon 1.0.9 h2bbff1b_7
libbrotlidec 1.0.9 h2bbff1b_7
libbrotlienc 1.0.9 h2bbff1b_7
libclang 16.0.6 pypi_0 pypi
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
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
libzlib 1.2.13 hcfcfb64_5 conda-forge
libzlib-wapi 1.2.13 hcfcfb64_5 conda-forge
lz4-c 1.9.4 h2bbff1b_0
markdown 3.4.4 pypi_0 pypi
markupsafe 2.1.3 pypi_0 pypi
matplotlib 3.7.1 py310haa95532_1
matplotlib-base 3.7.1 py310h4ed8f06_1
mkl 2023.1.0 h8bd8f75_46356
mkl-service 2.4.0 py310h2bbff1b_1
mkl_fft 1.3.6 py310h4ed8f06_1
mkl_random 1.2.2 py310h4ed8f06_1
munkres 1.1.4 py_0
numexpr 2.8.4 py310h2cd9be0_1
numpy 1.25.0 py310h055cbcc_0
numpy-base 1.25.0 py310h65a83cf_0
nvidia-ml-py 12.535.77 pyhd8ed1ab_0 conda-forge
oauthlib 3.2.2 pypi_0 pypi
opencv-python 4.8.0.74 pypi_0 pypi
openssl 1.1.1u hcfcfb64_0 conda-forge
opt-einsum 3.3.0 pypi_0 pypi
packaging 23.0 py310haa95532_0
pcre 8.45 hd77b12b_0
pillow 9.4.0 py310hd77b12b_0
pip 23.2.1 py310haa95532_0
ply 3.11 py310haa95532_0
pooch 1.4.0 pyhd3eb1b0_0
protobuf 3.19.6 pypi_0 pypi
psutil 5.9.0 py310h2bbff1b_0
pyasn1 0.5.0 pypi_0 pypi
pyasn1-modules 0.3.0 pypi_0 pypi
pycparser 2.21 pyhd3eb1b0_0
pyopenssl 23.2.0 py310haa95532_0
pyparsing 3.0.9 py310haa95532_0
pyqt 5.15.7 py310hd77b12b_0
pyqt5-sip 12.11.0 py310hd77b12b_0
pysocks 1.7.1 py310haa95532_0
python 3.10.12 h966fe2a_0
python-dateutil 2.8.2 pyhd3eb1b0_0
python_abi 3.10 2_cp310 conda-forge
pywin32 305 py310h2bbff1b_0
pywinpty 2.0.2 py310h5da7b33_0
qt-main 5.15.2 he8e5bd7_8
qt-webengine 5.15.9 hb9a9bb5_5
qtwebkit 5.212 h2bbfb41_5
requests 2.31.0 py310haa95532_0
requests-oauthlib 1.3.1 pypi_0 pypi
rsa 4.9 pypi_0 pypi
scikit-learn 1.2.2 py310hd77b12b_1
scipy 1.10.1 py310h309d312_1
setuptools 68.0.0 py310haa95532_0
sip 6.6.2 py310hd77b12b_0
six 1.16.0 pyhd3eb1b0_1
sqlite 3.41.2 h2bbff1b_0
tbb 2021.8.0 h59b6b97_0
tensorboard 2.10.1 pypi_0 pypi
tensorboard-data-server 0.6.1 pypi_0 pypi
tensorboard-plugin-wit 1.8.1 pypi_0 pypi
tensorflow 2.10.1 pypi_0 pypi
tensorflow-estimator 2.10.0 pypi_0 pypi
tensorflow-io-gcs-filesystem 0.31.0 pypi_0 pypi
termcolor 2.3.0 pypi_0 pypi
threadpoolctl 2.2.0 pyh0d69192_0
tk 8.6.12 h2bbff1b_0
toml 0.10.2 pyhd3eb1b0_0
tornado 6.2 py310h2bbff1b_0
tqdm 4.65.0 py310h9909e9c_0
typing-extensions 4.7.1 pypi_0 pypi
tzdata 2023c h04d1e81_0
ucrt 10.0.22621.0 h57928b3_0 conda-forge
urllib3 1.26.16 py310haa95532_0
vc 14.2 h21ff451_1
vc14_runtime 14.36.32532 hfdfe4a8_17 conda-forge
vs2015_runtime 14.36.32532 h05e6639_17 conda-forge
werkzeug 2.3.6 pypi_0 pypi
wheel 0.38.4 py310haa95532_0
win_inet_pton 1.1.0 py310haa95532_0
winpty 0.4.3 4
wrapt 1.15.0 pypi_0 pypi
xz 5.4.2 h8cc25b3_0
zlib 1.2.13 hcfcfb64_5 conda-forge
zlib-wapi 1.2.13 hcfcfb64_5 conda-forge
zstd 1.5.5 hd43e919_0
================= Configs ==================
--------- .faceswap ---------
backend: nvidia
--------- 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.mask_blend]
type: normalized
kernel_size: 3
passes: 4
threshold: 4
erosion: 0.0
erosion_top: 0.0
erosion_bottom: 0.0
erosion_left: 0.0
erosion_right: 0.0
[scaling.sharpen]
method: none
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
separate_mask: False
jpg_quality: 75
png_compress_level: 3
[writer.pillow]
format: png
draw_transparent: False
separate_mask: False
optimize: False
gif_interlace: True
jpg_quality: 75
png_compress_level: 3
tif_compression: tiff_deflate
--------- extract.ini ---------
[global]
allow_growth: False
aligner_min_scale: 0.07
aligner_max_scale: 2.0
aligner_distance: 22.5
aligner_roll: 45.0
aligner_features: True
filter_refeed: True
save_filtered: False
realign_refeeds: True
filter_realign: True
[align.fan]
batch-size: 12
[detect.cv2_dnn]
confidence: 50
[detect.mtcnn]
minsize: 20
scalefactor: 0.709
batch-size: 8
cpu: True
threshold_1: 0.6
threshold_2: 0.7
threshold_3: 0.7
[detect.s3fd]
confidence: 70
batch-size: 4
[mask.bisenet_fp]
batch-size: 8
cpu: False
weights: faceswap
include_ears: False
include_hair: False
include_glasses: True
[mask.custom]
batch-size: 8
centering: face
fill: False
[mask.unet_dfl]
batch-size: 8
[mask.vgg_clear]
batch-size: 6
[mask.vgg_obstructed]
batch-size: 2
[recognition.vgg_face2]
batch-size: 16
cpu: False
--------- 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]
centering: face
coverage: 87.5
icnr_init: False
conv_aware_init: False
optimizer: adam
learning_rate: 5e-05
epsilon_exponent: -7
save_optimizer: exit
autoclip: False
reflect_padding: False
allow_growth: False
mixed_precision: False
nan_protection: True
convert_batchsize: 16
[global.loss]
loss_function: ssim
loss_function_2: mse
loss_weight_2: 100
loss_function_3: none
loss_weight_3: 0
loss_function_4: none
loss_weight_4: 0
mask_loss_function: mse
eye_multiplier: 3
mouth_multiplier: 2
penalized_mask_loss: True
mask_type: extended
mask_blur_kernel: 3
mask_threshold: 4
learn_mask: False
[model.dfaker]
output_size: 128
[model.dfl_h128]
lowmem: False
[model.dfl_sae]
input_size: 128
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.phaze_a]
output_size: 128
shared_fc: none
enable_gblock: True
split_fc: True
split_gblock: False
split_decoders: False
enc_architecture: fs_original
enc_scaling: 7
enc_load_weights: True
bottleneck_type: dense
bottleneck_norm: none
bottleneck_size: 1024
bottleneck_in_encoder: True
fc_depth: 1
fc_min_filters: 1024
fc_max_filters: 1024
fc_dimensions: 4
fc_filter_slope: -0.5
fc_dropout: 0.0
fc_upsampler: upsample2d
fc_upsamples: 1
fc_upsample_filters: 512
fc_gblock_depth: 3
fc_gblock_min_nodes: 512
fc_gblock_max_nodes: 512
fc_gblock_filter_slope: -0.5
fc_gblock_dropout: 0.0
dec_upscale_method: subpixel
dec_upscales_in_fc: 0
dec_norm: none
dec_min_filters: 64
dec_max_filters: 512
dec_slope_mode: full
dec_filter_slope: -0.45
dec_res_blocks: 1
dec_output_kernel: 5
dec_gaussian: True
dec_skip_last_residual: True
freeze_layers: keras_encoder
load_layers: encoder
fs_original_depth: 4
fs_original_min_filters: 128
fs_original_max_filters: 1024
fs_original_use_alt: False
mobilenet_width: 1.0
mobilenet_depth: 1
mobilenet_dropout: 0.001
mobilenet_minimalistic: 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
nodes: 1024
complexity_encoder: 128
complexity_decoder_a: 384
complexity_decoder_b: 512
[model.villain]
lowmem: False
[trainer.original]
preview_images: 14
mask_opacity: 30
mask_color: #ff0000
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