mmmikhailov commented 5 years ago

Expected behavior

My 1st try to faceswap. Training process crash.

Actual behavior

Loading... 03/14/2019 10:28:19 INFO Log level set to: INFO Using TensorFlow backend. 03/14/2019 10:28:21 INFO Model A Directory: C:\faceswap\Photo\Person1 03/14/2019 10:28:21 INFO Model B Directory: C:\faceswap\Photo\Person2 03/14/2019 10:28:21 INFO Training data directory: C:\faceswap\models 03/14/2019 10:28:21 INFO ===================================================================== 03/14/2019 10:28:21 INFO - Using live preview - 03/14/2019 10:28:21 INFO - Press 'ENTER' on the preview window to save and quit - 03/14/2019 10:28:21 INFO - Press 'S' on the preview window to save model weights immediately - 03/14/2019 10:28:21 INFO ===================================================================== 03/14/2019 10:28:22 INFO Loading data, this may take a while... 03/14/2019 10:28:22 INFO Loading Model from Original plugin... 03/14/2019 10:28:24 INFO Loading config: 'C:\faceswap\config\train.ini' 03/14/2019 10:28:24 WARNING No existing state file found. Generating. 03/14/2019 10:28:25 INFO Creating new 'original' model in folder: 'C:\faceswap\models' 03/14/2019 10:28:25 INFO Loading Trainer from Original plugin... 03/14/2019 10:28:25 ERROR 'NoneType' object has no attribute 'astype' Traceback (most recent call last): File "C:\faceswap\lib\multithreading.py", line 261, in _runner target(*args, *kwargs) File "C:\faceswap\lib\training_data.py", line 105, in load_batches imgs = self.process_face(img_path, side, is_timelapse) File "C:\faceswap\lib\training_data.py", line 155, in process_face image = self.processing.color_adjust(image) File "C:\faceswap\lib\training_data.py", line 226, in color_adjust return img.astype('float32') / 255.0 AttributeError: 'NoneType' object has no attribute 'astype' 03/14/2019 10:28:27 INFO Enabled TensorBoard Logging 03/14/2019 10:28:34 CRITICAL Error caught! Exiting... 03/14/2019 10:28:34 ERROR Caught exception in thread: 'training_0' 03/14/2019 10:28:36 ERROR Got Exception on main handler: Traceback (most recent call last): File "C:\faceswap\lib\cli.py", line 107, in execute_script process.process() File "C:\faceswap\scripts\train.py", line 101, in process self.end_thread(thread, err) File "C:\faceswap\scripts\train.py", line 126, in end_thread thread.join() File "C:\faceswap\lib\multithreading.py", line 443, in join raise thread.err[1].with_traceback(thread.err[2]) File "C:\faceswap\lib\multithreading.py", line 381, in run self._target(self._args, **self._kwargs) File "C:\faceswap\scripts\train.py", line 152, in training raise err File "C:\faceswap\scripts\train.py", line 142, in training self.run_training_cycle(model, trainer) File "C:\faceswap\scripts\train.py", line 214, in run_training_cycle trainer.train_one_step(viewer, timelapse) File "C:\faceswap\plugins\train\trainer_base.py", line 139, in train_one_step loss[side] = batcher.train_one_batch(do_preview) File "C:\faceswap\plugins\train\trainer_base.py", line 213, in train_one_batch batch = self.get_next(do_preview) File "C:\faceswap\plugins\train\trainer_base.py", line 221, in get_next batch = next(self.feed) StopIteration 03/14/2019 10:28:36 CRITICAL An unexpected crash has occurred. Crash report written to C:\faceswap\crash_report.2019.03.14.102834486501.log. Please verify you are running the latest version of faceswap before reporting Process exited.

Steps to reproduce

Simple training session via GUI.

Other relevant information

============ System Information ============ encoding: cp1251 git_branch: master git_commits: 7ae44c7 fix on gaussian sharpen gpu_cuda: 10.0 gpu_cudnn: 7.4.1 gpu_devices: GPU_0: GeForce GTX 1070, GPU_1: GeForce GTX 1070 gpu_driver: 419.35 gpu_vram: GPU_0: 8192MB, GPU_1: 8192MB os_machine: AMD64 os_platform: Windows-10-10.0.17134-SP0 os_release: 10 py_command: C:\faceswap/faceswap.py gui py_conda_version: conda 4.5.12 py_implementation: CPython py_version: 3.6.8 py_virtual_env: True sys_cores: 6 sys_processor: Intel64 Family 6 Model 158 Stepping 10, GenuineIntel sys_ram: Total: 16317MB, Available: 10754MB, Used: 5563MB, Free: 10754MB

=============== Pip Packages =============== absl-py==0.7.0 astor==0.7.1 certifi==2019.3.9 Click==7.0 cloudpickle==0.8.0 cmake==3.13.3 cycler==0.10.0 cytoolz==0.9.0.1 dask==1.1.4 decorator==4.3.2 dlib==19.16.99 face-recognition==1.2.3 face-recognition-models==0.3.0 ffmpy==0.2.2 gast==0.2.2 grpcio==1.16.1 h5py==2.9.0 imageio==2.5.0 Keras==2.2.4 Keras-Applications==1.0.7 Keras-Preprocessing==1.0.9 kiwisolver==1.0.1 Markdown==3.0.1 matplotlib==2.2.2 mkl-fft==1.0.10 mkl-random==1.0.2 mock==2.0.0 networkx==2.2 numpy==1.15.4 nvidia-ml-py3==7.352.0 olefile==0.46 opencv-python==4.0.0.21 pathlib==1.0.1 pbr==5.1.3 Pillow==5.4.1 protobuf==3.6.1 psutil==5.6.1 pyparsing==2.3.1 pyreadline==2.1 python-dateutil==2.8.0 pytz==2018.9 PyWavelets==1.0.2 PyYAML==3.13 scikit-image==0.14.2 scikit-learn==0.20.3 scipy==1.2.1 six==1.12.0 tensorboard==1.12.2 tensorflow==1.12.0 tensorflow-estimator==1.13.0 termcolor==1.1.0 toolz==0.9.0 tornado==6.0.1 tqdm==4.31.1 Werkzeug==0.14.1 wincertstore==0.2

============== Conda Packages ==============

packages in environment at C:\Users\User\MiniConda3\envs\faceswap:

#

Kirin-kun commented 5 years ago

Check your datasets to see if there are no faces with a different size than the others (128x128 instead of 256x256 for example).

I had similar crashes at the batch building step because of that. All faces, in both A and B, must be the same size.

bryanlyon commented 5 years ago

Closing for non-response. If you're still experiencing this issue, please comment here.

deepfakes / faceswap-playground

Unable to train (critical error after TensorBoard Logging) #269

Expected behavior

Actual behavior

Steps to reproduce

Other relevant information

packages in environment at C:\Users\User\MiniConda3\envs\faceswap:

Name Version Build Channel