Hi all, can you please help me?
I've got a problem as soon as the train starts.
I'm using the Windows interface with all standard settings.
The generated command is this:
C:\Users\asusI7\anaconda3\envs\deepFake\python.exe C:\Users\asusI7\Documents\td\faceswap\faceswap.py train -A C:/Users/asusI7/Documents/td/faceswap/facceSimplo -B C:/Users/asusI7/Documents/td/faceswap/facceBritney -m C:/Users/asusI7/Documents/td/faceswap/originals -t original -bs 64 -it 1000000 -g 1 -s 100 -ss 25000 -ps 50 -L INFO
I would like to attach the log, but I don't know how. It is too long to copy here.
Please let me know how can I send it to you, it it helps.
Here's the message I received on the GUI:
Code: Select all
Loading...
Setting Faceswap backend to NVIDIA
04/05/2020 19:35:03 INFO Log level set to: INFO
Using TensorFlow backend.
04/05/2020 19:35:05 INFO Model A Directory: C:\Users\asusI7\Documents\td\faceswap\facceSimplo
04/05/2020 19:35:05 INFO Model B Directory: C:\Users\asusI7\Documents\td\faceswap\facceBritney
04/05/2020 19:35:05 INFO Training data directory: C:\Users\asusI7\Documents\td\faceswap\originals
04/05/2020 19:35:05 INFO ===================================================
04/05/2020 19:35:05 INFO Starting
04/05/2020 19:35:05 INFO Press 'Stop' to save and quit
04/05/2020 19:35:05 INFO ===================================================
04/05/2020 19:35:06 INFO Loading data, this may take a while...
04/05/2020 19:35:06 INFO Loading Model from Original plugin...
04/05/2020 19:35:06 INFO No existing state file found. Generating.
04/05/2020 19:35:08 INFO Creating new 'original' model in folder: 'C:\Users\asusI7\Documents\td\faceswap\originals'
04/05/2020 19:35:08 INFO Loading Trainer from Original plugin...
04/05/2020 19:35:10 INFO Enabled TensorBoard Logging
2020-04-05 19:35:19.647184: E tensorflow/stream_executor/cuda/cuda_driver.cc:1006] failed to synchronize the stop event: CUDA_ERROR_LAUNCH_FAILED: unspecified launch failure
2020-04-05 19:35:19.647484: E tensorflow/stream_executor/gpu/gpu_timer.cc:55] Internal: error destroying CUDA event in context 0x22f0970d220: CUDA_ERROR_LAUNCH_FAILED: unspecified launch failure
2020-04-05 19:35:19.647676: E tensorflow/stream_executor/gpu/gpu_timer.cc:60] Internal: error destroying CUDA event in context 0x22f0970d220: CUDA_ERROR_LAUNCH_FAILED: unspecified launch failure
2020-04-05 19:35:19.647895: E tensorflow/stream_executor/cuda/cuda_driver.cc:704] failed to enqueue async memset operation: CUDA_ERROR_LAUNCH_FAILED: unspecified launch failure
2020-04-05 19:35:19.648098: E tensorflow/stream_executor/cuda/cuda_driver.cc:625] failed to load PTX text as a module: CUDA_ERROR_LAUNCH_FAILED: unspecified launch failure
2020-04-05 19:35:19.648286: E tensorflow/stream_executor/cuda/cuda_driver.cc:630] error log buffer (1024 bytes):
2020-04-05 19:35:19.648477: E tensorflow/stream_executor/cuda/cuda_driver.cc:625] failed to load PTX text as a module: CUDA_ERROR_LAUNCH_FAILED: unspecified launch failure
2020-04-05 19:35:19.648654: E tensorflow/stream_executor/cuda/cuda_driver.cc:630] error log buffer (1024 bytes):
04/05/2020 19:35:20 CRITICAL Error caught! Exiting...
04/05/2020 19:35:20 ERROR Caught exception in thread: '_training_0'
04/05/2020 19:35:23 ERROR Got Exception on main handler:
Traceback (most recent call last):
File "C:\Users\asusI7\Documents\td\faceswap\lib\cli.py", line 128, in execute_script
process.process()
File "C:\Users\asusI7\Documents\td\faceswap\scripts\train.py", line 159, in process
self._end_thread(thread, err)
File "C:\Users\asusI7\Documents\td\faceswap\scripts\train.py", line 199, in _end_thread
thread.join()
File "C:\Users\asusI7\Documents\td\faceswap\lib\multithreading.py", line 121, in join
raise thread.err[1].with_traceback(thread.err[2])
File "C:\Users\asusI7\Documents\td\faceswap\lib\multithreading.py", line 37, in run
self._target(*self._args, **self._kwargs)
File "C:\Users\asusI7\Documents\td\faceswap\scripts\train.py", line 224, in _training
raise err
File "C:\Users\asusI7\Documents\td\faceswap\scripts\train.py", line 214, in _training
self._run_training_cycle(model, trainer)
File "C:\Users\asusI7\Documents\td\faceswap\scripts\train.py", line 303, in _run_training_cycle
trainer.train_one_step(viewer, timelapse)
File "C:\Users\asusI7\Documents\td\faceswap\plugins\train\trainer\_base.py", line 316, in train_one_step
raise err
File "C:\Users\asusI7\Documents\td\faceswap\plugins\train\trainer\_base.py", line 283, in train_one_step
loss[side] = batcher.train_one_batch()
File "C:\Users\asusI7\Documents\td\faceswap\plugins\train\trainer\_base.py", line 424, in train_one_batch
loss = self._model.predictors[self._side].train_on_batch(model_inputs, model_targets)
File "C:\Users\asusI7\anaconda3\envs\deepFake\lib\site-packages\keras\engine\training.py", line 1217, in train_on_batch
outputs = self.train_function(ins)
File "C:\Users\asusI7\anaconda3\envs\deepFake\lib\site-packages\keras\backend\tensorflow_backend.py", line 2715, in __call__
return self._call(inputs)
File "C:\Users\asusI7\anaconda3\envs\deepFake\lib\site-packages\keras\backend\tensorflow_backend.py", line 2675, in _call
fetched = self._callable_fn(*array_vals)
File "C:\Users\asusI7\anaconda3\envs\deepFake\lib\site-packages\tensorflow_core\python\client\session.py", line 1472, in __call__
run_metadata_ptr)
tensorflow.python.framework.errors_impl.InternalError: 2 root error(s) found.
(0) Internal: cuDNN launch failure : input shape([64,1024,4,4]) filter shape([3,3,1024,2048])
[[{{node encoder/upscale_4_0_conv2d/convolution}}]]
[[loss/mul/_295]]
(1) Internal: cuDNN launch failure : input shape([64,1024,4,4]) filter shape([3,3,1024,2048])
[[{{node encoder/upscale_4_0_conv2d/convolution}}]]
0 successful operations.
0 derived errors ignored.
04/05/2020 19:35:23 CRITICAL An unexpected crash has occurred. Crash report written to 'C:\Users\asusI7\Documents\td\faceswap\crash_report.2020.04.05.193523012010.log'. You MUST provide this file if seeking assistance. Please verify you are running the latest version of faceswap before reporting
Process exited.