plaidml.exceptions.ResourceExhausted: Unable to allocate SVM memory

If training is failing to start, and you are not receiving an error message telling you what to do, tell us about it here


Forum rules

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

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

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

Locked
User avatar
TheAwesomeYT
Posts: 1
Joined: Tue Jun 02, 2020 7:49 pm

plaidml.exceptions.ResourceExhausted: Unable to allocate SVM memory

Post by TheAwesomeYT »

For some reason I always get this error, and I would really like some help on what it means and how to fix it.

Code: Select all

06/02/2020 20:07:11 MainProcess     ThreadPoolExecutor-16_1 _base           save                      DEBUG    Saving model: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_decoder_B.h5'
06/02/2020 20:07:11 MainProcess     ThreadPoolExecutor-16_0 _base           save                      DEBUG    Saving model: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_decoder_A.h5'
06/02/2020 20:07:11 MainProcess     ThreadPoolExecutor-16_2 _base           save                      DEBUG    Saving model: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_encoder.h5'
06/02/2020 20:07:11 MainProcess     ThreadPoolExecutor-16_3 serializer      save                      DEBUG    filename: C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_state.json, data type: <class 'dict'>
06/02/2020 20:07:11 MainProcess     ThreadPoolExecutor-16_3 serializer      _check_extension          DEBUG    Original filename: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_state.json', final filename: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_state.json'
06/02/2020 20:07:11 MainProcess     ThreadPoolExecutor-16_3 serializer      marshal                   DEBUG    data type: <class 'dict'>
06/02/2020 20:07:11 MainProcess     ThreadPoolExecutor-16_3 serializer      marshal                   DEBUG    returned data type: <class 'bytes'>
06/02/2020 20:07:11 MainProcess     ThreadPoolExecutor-16_3 _base           save                      DEBUG    Saved State
06/02/2020 20:07:16 MainProcess     _training_0     _base           save_models               INFO     [Saved models] - Average since last save: face_loss_A: 0.21554, face_loss_B: 0.17824
06/02/2020 23:06:59 MainProcess     _training_0     _base           generate_preview          DEBUG    Generating preview
06/02/2020 23:06:59 MainProcess     _training_0     _base           largest_face_index        DEBUG    0
06/02/2020 23:06:59 MainProcess     _training_0     _base           compile_sample            DEBUG    Compiling samples: (side: 'a', samples: 14)
06/02/2020 23:08:03 MainProcess     _training_0     _base           generate_preview          DEBUG    Generating preview
06/02/2020 23:08:03 MainProcess     _training_0     _base           largest_face_index        DEBUG    0
06/02/2020 23:08:03 MainProcess     _training_0     _base           compile_sample            DEBUG    Compiling samples: (side: 'b', samples: 14)
06/02/2020 23:08:03 MainProcess     _training_0     _base           show_sample               DEBUG    Showing sample
06/02/2020 23:08:03 MainProcess     _training_0     _base           _get_predictions          DEBUG    Getting Predictions
06/02/2020 23:08:15 MainProcess     _training_0     _base           _get_predictions          DEBUG    Returning predictions: {'a_a': (14, 64, 64, 3), 'b_a': (14, 64, 64, 3), 'a_b': (14, 64, 64, 3), 'b_b': (14, 64, 64, 3)}
06/02/2020 23:08:15 MainProcess     _training_0     _base           _to_full_frame            DEBUG    side: 'a', number of sample arrays: 3, prediction.shapes: [(14, 64, 64, 3), (14, 64, 64, 3)])
06/02/2020 23:08:15 MainProcess     _training_0     _base           _frame_overlay            DEBUG    full_size: 256, target_size: 176, color: (0, 0, 255)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _frame_overlay            DEBUG    Overlayed background. Shape: (14, 256, 256, 3)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resizing sample: (side: 'a', sample.shape: (14, 64, 64, 3), target_size: 176, scale: 2.75)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resized sample: (side: 'a' shape: (14, 176, 176, 3))
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resizing sample: (side: 'a', sample.shape: (14, 64, 64, 3), target_size: 176, scale: 2.75)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resized sample: (side: 'a' shape: (14, 176, 176, 3))
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resizing sample: (side: 'a', sample.shape: (14, 64, 64, 3), target_size: 176, scale: 2.75)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resized sample: (side: 'a' shape: (14, 176, 176, 3))
06/02/2020 23:08:15 MainProcess     _training_0     _base           _overlay_foreground       DEBUG    Overlayed foreground. Shape: (14, 256, 256, 3)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _overlay_foreground       DEBUG    Overlayed foreground. Shape: (14, 256, 256, 3)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _overlay_foreground       DEBUG    Overlayed foreground. Shape: (14, 256, 256, 3)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resizing sample: (side: 'a', sample.shape: (14, 256, 256, 3), target_size: 128, scale: 0.5)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resized sample: (side: 'a' shape: (14, 128, 128, 3))
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resizing sample: (side: 'a', sample.shape: (14, 256, 256, 3), target_size: 128, scale: 0.5)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resized sample: (side: 'a' shape: (14, 128, 128, 3))
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resizing sample: (side: 'a', sample.shape: (14, 256, 256, 3), target_size: 128, scale: 0.5)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resized sample: (side: 'a' shape: (14, 128, 128, 3))
06/02/2020 23:08:15 MainProcess     _training_0     _base           _get_headers              DEBUG    side: 'a', width: 128
06/02/2020 23:08:15 MainProcess     _training_0     _base           _get_headers              DEBUG    height: 32, total_width: 384
06/02/2020 23:08:15 MainProcess     _training_0     _base           _get_headers              DEBUG    texts: ['Original (A)', 'Original > Original', 'Original > Swap'], text_sizes: [(72, 9), (116, 9), (102, 9)], text_x: [28, 134, 269], text_y: 20
06/02/2020 23:08:15 MainProcess     _training_0     _base           _get_headers              DEBUG    header_box.shape: (32, 384, 3)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _to_full_frame            DEBUG    side: 'b', number of sample arrays: 3, prediction.shapes: [(14, 64, 64, 3), (14, 64, 64, 3)])
06/02/2020 23:08:15 MainProcess     _training_0     _base           _frame_overlay            DEBUG    full_size: 256, target_size: 176, color: (0, 0, 255)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _frame_overlay            DEBUG    Overlayed background. Shape: (14, 256, 256, 3)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resizing sample: (side: 'b', sample.shape: (14, 64, 64, 3), target_size: 176, scale: 2.75)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resized sample: (side: 'b' shape: (14, 176, 176, 3))
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resizing sample: (side: 'b', sample.shape: (14, 64, 64, 3), target_size: 176, scale: 2.75)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resized sample: (side: 'b' shape: (14, 176, 176, 3))
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resizing sample: (side: 'b', sample.shape: (14, 64, 64, 3), target_size: 176, scale: 2.75)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resized sample: (side: 'b' shape: (14, 176, 176, 3))
06/02/2020 23:08:15 MainProcess     _training_0     _base           _overlay_foreground       DEBUG    Overlayed foreground. Shape: (14, 256, 256, 3)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _overlay_foreground       DEBUG    Overlayed foreground. Shape: (14, 256, 256, 3)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _overlay_foreground       DEBUG    Overlayed foreground. Shape: (14, 256, 256, 3)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resizing sample: (side: 'b', sample.shape: (14, 256, 256, 3), target_size: 128, scale: 0.5)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resized sample: (side: 'b' shape: (14, 128, 128, 3))
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resizing sample: (side: 'b', sample.shape: (14, 256, 256, 3), target_size: 128, scale: 0.5)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resized sample: (side: 'b' shape: (14, 128, 128, 3))
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resizing sample: (side: 'b', sample.shape: (14, 256, 256, 3), target_size: 128, scale: 0.5)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _resize_sample            DEBUG    Resized sample: (side: 'b' shape: (14, 128, 128, 3))
06/02/2020 23:08:15 MainProcess     _training_0     _base           _get_headers              DEBUG    side: 'b', width: 128
06/02/2020 23:08:15 MainProcess     _training_0     _base           _get_headers              DEBUG    height: 32, total_width: 384
06/02/2020 23:08:15 MainProcess     _training_0     _base           _get_headers              DEBUG    texts: ['Swap (B)', 'Swap > Swap', 'Swap > Original'], text_sizes: [(59, 9), (87, 9), (102, 9)], text_x: [34, 148, 269], text_y: 20
06/02/2020 23:08:15 MainProcess     _training_0     _base           _get_headers              DEBUG    header_box.shape: (32, 384, 3)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _duplicate_headers        DEBUG    side: a header.shape: (32, 384, 3)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _duplicate_headers        DEBUG    side: b header.shape: (32, 384, 3)
06/02/2020 23:08:15 MainProcess     _training_0     _base           _stack_images             DEBUG    Stack images
06/02/2020 23:08:15 MainProcess     _training_0     _base           get_transpose_axes        DEBUG    Even number of images to stack
06/02/2020 23:08:15 MainProcess     _training_0     _base           _stack_images             DEBUG    Stacked images
06/02/2020 23:08:15 MainProcess     _training_0     _base           show_sample               DEBUG    Compiled sample
06/02/2020 23:08:16 MainProcess     _training_0     _base           save_models               DEBUG    Backing up and saving models
06/02/2020 23:08:16 MainProcess     _training_0     _base           get_save_averages         DEBUG    Getting save averages
06/02/2020 23:08:16 MainProcess     _training_0     _base           get_save_averages         DEBUG    Average losses since last save: {'a': 0.10190289102494716, 'b': 0.1120093747228384}
06/02/2020 23:08:16 MainProcess     _training_0     _base           check_loss_drop           DEBUG    Loss for 'a' has dropped
06/02/2020 23:08:16 MainProcess     _training_0     _base           check_loss_drop           DEBUG    Loss for 'b' has dropped
06/02/2020 23:08:16 MainProcess     _training_0     _base           should_backup             DEBUG    Lowest historical save iteration loss average: {'a': 0.21553638577461243, 'b': 0.1782432198524475}
06/02/2020 23:08:16 MainProcess     _training_0     _base           should_backup             DEBUG    Updating lowest save iteration average for 'a': 0.10190289102494716
06/02/2020 23:08:16 MainProcess     _training_0     _base           should_backup             DEBUG    Updating lowest save iteration average for 'b': 0.1120093747228384
06/02/2020 23:08:16 MainProcess     _training_0     _base           should_backup             DEBUG    Backing up: True
06/02/2020 23:08:16 MainProcess     _training_0     _base           save_models               INFO     Backing up models...
06/02/2020 23:08:16 MainProcess     ThreadPoolExecutor-219_0 backup_restore  backup_model              VERBOSE  Backing up: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_decoder_A.h5' to 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_decoder_A.h5.bk'
06/02/2020 23:08:16 MainProcess     ThreadPoolExecutor-219_1 backup_restore  backup_model              VERBOSE  Backing up: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_decoder_B.h5' to 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_decoder_B.h5.bk'
06/02/2020 23:08:16 MainProcess     ThreadPoolExecutor-219_2 backup_restore  backup_model              VERBOSE  Backing up: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_encoder.h5' to 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_encoder.h5.bk'
06/02/2020 23:08:16 MainProcess     ThreadPoolExecutor-219_3 _base           save                      DEBUG    Saving State
06/02/2020 23:08:16 MainProcess     ThreadPoolExecutor-219_3 backup_restore  backup_model              VERBOSE  Backing up: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_state.json' to 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_state.json.bk'
06/02/2020 23:08:16 MainProcess     ThreadPoolExecutor-219_1 _base           save                      DEBUG    Saving model: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_decoder_B.h5'
06/02/2020 23:08:16 MainProcess     ThreadPoolExecutor-219_2 _base           save                      DEBUG    Saving model: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_encoder.h5'
06/02/2020 23:08:16 MainProcess     ThreadPoolExecutor-219_0 _base           save                      DEBUG    Saving model: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_decoder_A.h5'
06/02/2020 23:08:16 MainProcess     ThreadPoolExecutor-219_3 serializer      save                      DEBUG    filename: C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_state.json, data type: <class 'dict'>
06/02/2020 23:08:16 MainProcess     ThreadPoolExecutor-219_3 serializer      _check_extension          DEBUG    Original filename: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_state.json', final filename: 'C:\Users\HP Pavilion\Desktop\deepface\jeezz\original_state.json'
06/02/2020 23:08:16 MainProcess     ThreadPoolExecutor-219_3 serializer      marshal                   DEBUG    data type: <class 'dict'>
06/02/2020 23:08:16 MainProcess     ThreadPoolExecutor-219_3 serializer      marshal                   DEBUG    returned data type: <class 'bytes'>
06/02/2020 23:08:16 MainProcess     ThreadPoolExecutor-219_3 _base           save                      DEBUG    Saved State
06/02/2020 23:08:34 MainProcess     _training_0     _base           save_models               INFO     [Saved models] - Average since last save: face_loss_A: 0.10190, face_loss_B: 0.11201
06/02/2020 23:52:27 MainProcess     MainThread      train           _monitor                  DEBUG    Thread error detected
06/02/2020 23:52:27 MainProcess     _training_0     multithreading  run                       DEBUG    Error in thread (_training_0): Unable to allocate SVM memory
06/02/2020 23:52:27 MainProcess     MainThread      train           _monitor                  DEBUG    Closed Monitor
06/02/2020 23:52:27 MainProcess     MainThread      train           _end_thread               DEBUG    Ending Training thread
06/02/2020 23:52:27 MainProcess     MainThread      train           _end_thread               CRITICAL Error caught! Exiting...
06/02/2020 23:52:27 MainProcess     MainThread      multithreading  join                      DEBUG    Joining Threads: '_training'
06/02/2020 23:52:27 MainProcess     MainThread      multithreading  join                      DEBUG    Joining Thread: '_training_0'
06/02/2020 23:52:27 MainProcess     MainThread      multithreading  join                      ERROR    Caught exception in thread: '_training_0'
Traceback (most recent call last):
  File "C:\Users\HP Pavilion\faceswap\lib\cli\launcher.py", line 155, in execute_script
    process.process()
  File "C:\Users\HP Pavilion\faceswap\scripts\train.py", line 161, in process
    self._end_thread(thread, err)
  File "C:\Users\HP Pavilion\faceswap\scripts\train.py", line 201, in _end_thread
    thread.join()
  File "C:\Users\HP Pavilion\faceswap\lib\multithreading.py", line 121, in join
    raise thread.err[1].with_traceback(thread.err[2])
  File "C:\Users\HP Pavilion\faceswap\lib\multithreading.py", line 37, in run
    self._target(*self._args, **self._kwargs)
  File "C:\Users\HP Pavilion\faceswap\scripts\train.py", line 226, in _training
    raise err
  File "C:\Users\HP Pavilion\faceswap\scripts\train.py", line 216, in _training
    self._run_training_cycle(model, trainer)
  File "C:\Users\HP Pavilion\faceswap\scripts\train.py", line 305, in _run_training_cycle
    trainer.train_one_step(viewer, timelapse)
  File "C:\Users\HP Pavilion\faceswap\plugins\train\trainer\_base.py", line 316, in train_one_step
    raise err
  File "C:\Users\HP Pavilion\faceswap\plugins\train\trainer\_base.py", line 283, in train_one_step
    loss[side] = batcher.train_one_batch()
  File "C:\Users\HP Pavilion\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\HP Pavilion\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\training.py", line 1217, in train_on_batch
    outputs = self.train_function(ins)
  File "C:\Users\HP Pavilion\MiniConda3\envs\faceswap\lib\site-packages\plaidml\keras\backend.py", line 175, in __call__
    self._invoker.invoke()
  File "C:\Users\HP Pavilion\MiniConda3\envs\faceswap\lib\site-packages\plaidml\__init__.py", line 1455, in invoke
    return Invocation(self._ctx, self)
  File "C:\Users\HP Pavilion\MiniConda3\envs\faceswap\lib\site-packages\plaidml\__init__.py", line 1464, in __init__
    self._as_parameter_ = _lib().plaidml_schedule_invocation(ctx, invoker)
  File "C:\Users\HP Pavilion\MiniConda3\envs\faceswap\lib\site-packages\plaidml\__init__.py", line 777, in _check_err
    self.raise_last_status()
  File "C:\Users\HP Pavilion\MiniConda3\envs\faceswap\lib\site-packages\plaidml\library.py", line 131, in raise_last_status
    raise self.last_status()
plaidml.exceptions.ResourceExhausted: Unable to allocate SVM memory

============ System Information ============
encoding:            cp1252
git_branch:          master
git_commits:         ac40b0f Remove subpixel upscaling option (#1024)
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: Advanced Micro Devices, Inc. - Stoney (experimental)
gpu_devices_active:  GPU_0
gpu_driver:          ['3075.12']
gpu_vram:            GPU_0: 1378MB
os_machine:          AMD64
os_platform:         Windows-10-10.0.18362-SP0
os_release:          10
py_command:          C:\Users\HP Pavilion\faceswap\faceswap.py train -A C:/Users/HP Pavilion/Desktop/deepface/orig -ala C:/Users/HP Pavilion/Desktop/data_dst/alignments.fsa -B C:/Users/HP Pavilion/Desktop/deepface/otp -alb C:/Users/HP Pavilion/Desktop/data_src/alignments.fsa -m C:/Users/HP Pavilion/Desktop/deepface/jeezz -t original -bs 64 -it 100000 -s 100 -ss 25000 -ps 50 -nac -L INFO -gui
py_conda_version:    conda 4.8.3
py_implementation:   CPython
py_version:          3.7.7
py_virtual_env:      True
sys_cores:           2
sys_processor:       AMD64 Family 21 Model 112 Stepping 0, AuthenticAMD
sys_ram:             Total: 3974MB, Available: 463MB, Used: 3511MB, Free: 463MB

=============== Pip Packages ===============


============== Conda Packages ==============
# packages in environment at C:\Users\HP Pavilion\MiniConda3\envs\faceswap:
#
# Name                    Version                   Build  Channel
_tflow_select             2.2.0                     eigen  
absl-py 0.9.0 py37_0
astor 0.8.0 py37_0
blas 1.0 mkl
blinker 1.4 py37_0
ca-certificates 2020.1.1 0
cachetools 3.1.1 py_0
certifi 2020.4.5.1 py37_0
cffi 1.14.0 py37h7a1dbc1_0
chardet 3.0.4 py37_1003
click 7.1.2 py_0
cloudpickle 1.4.1 py_0
cryptography 2.9.2 py37h7a1dbc1_0
cycler 0.10.0 py37_0
cytoolz 0.10.1 py37he774522_0
dask-core 2.17.0 py_0
decorator 4.4.2 py_0
enum34 1.1.10 pypi_0 pypi fastcluster 1.1.26 py37he350917_0 conda-forge ffmpeg 4.2.3 ha925a31_0 conda-forge ffmpy 0.2.2 pypi_0 pypi freetype 2.9.1 ha9979f8_1
gast 0.2.2 py37_0
git 2.23.0 h6bb4b03_0
google-auth 1.14.1 py_0
google-auth-oauthlib 0.4.1 py_2
google-pasta 0.2.0 py_0
grpcio 1.27.2 py37h351948d_0
h5py 2.9.0 py37h5e291fa_0
hdf5 1.10.4 h7ebc959_0
icc_rt 2019.0.0 h0cc432a_1
icu 58.2 ha925a31_3
idna 2.9 py_1
imageio 2.6.1 py37_0
imageio-ffmpeg 0.4.2 py_0 conda-forge intel-openmp 2020.1 216
joblib 0.15.1 py_0
jpeg 9b hb83a4c4_2
keras 2.2.4 0
keras-applications 1.0.8 py_0
keras-base 2.2.4 py37_0
keras-preprocessing 1.1.0 py_1
kiwisolver 1.2.0 py37h74a9793_0
libpng 1.6.37 h2a8f88b_0
libprotobuf 3.11.4 h7bd577a_0
libtiff 4.1.0 h56a325e_0
markdown 3.1.1 py37_0
matplotlib 3.1.1 py37hc8f65d3_0
matplotlib-base 3.1.3 py37h64f37c6_0
mkl 2020.1 216
mkl-service 2.3.0 py37hb782905_0
mkl_fft 1.0.15 py37h14836fe_0
mkl_random 1.1.1 py37h47e9c7a_0
networkx 2.4 py_0
numpy 1.17.4 py37h4320e6b_0
numpy-base 1.17.4 py37hc3f5095_0
nvidia-ml-py3 7.352.1 pypi_0 pypi oauthlib 3.1.0 py_0
olefile 0.46 py37_0
opencv-python 4.1.2.30 pypi_0 pypi openssl 1.1.1g he774522_0
opt_einsum 3.1.0 py_0
pathlib 1.0.1 py37_1
pillow 6.2.1 py37hdc69c19_0
pip 20.0.2 py37_3
plaidml 0.6.4 pypi_0 pypi plaidml-keras 0.6.4 pypi_0 pypi protobuf 3.11.4 py37h33f27b4_0
psutil 5.7.0 py37he774522_0
pyasn1 0.4.8 py_0
pyasn1-modules 0.2.7 py_0
pycparser 2.20 py_0
pyjwt 1.7.1 py37_0
pyopenssl 19.1.0 py37_0
pyparsing 2.4.7 py_0
pyqt 5.9.2 py37h6538335_2
pyreadline 2.1 py37_1
pysocks 1.7.1 py37_0
python 3.7.7 h81c818b_4
python-dateutil 2.8.1 py_0
python_abi 3.7 1_cp37m conda-forge pytz 2020.1 py_0
pywavelets 1.1.1 py37he774522_0
pywin32 227 py37he774522_1
pyyaml 5.3.1 py37he774522_0
qt 5.9.7 vc14h73c81de_0
requests 2.23.0 py37_0
requests-oauthlib 1.3.0 py_0
rsa 4.0 py_0
scikit-image 0.16.2 py37h47e9c7a_0
scikit-learn 0.22.1 py37h6288b17_0
scipy 1.4.1 py37h9439919_0
setuptools 46.4.0 py37_0
sip 4.19.8 py37h6538335_0
six 1.14.0 py37_0
sqlite 3.31.1 h2a8f88b_1
tensorboard 2.2.1 pyh532a8cf_0
tensorboard-plugin-wit 1.6.0 py_0
tensorflow 1.15.0 eigen_py37h9f89a44_0
tensorflow-base 1.15.0 eigen_py37h07d2309_0
tensorflow-estimator 1.15.1 pyh2649769_0
termcolor 1.1.0 py37_1
tk 8.6.8 hfa6e2cd_0
toolz 0.10.0 py_0
toposort 1.5 py_3 conda-forge tornado 6.0.4 py37he774522_1
tqdm 4.46.0 py_0
urllib3 1.25.8 py37_0
vc 14.1 h0510ff6_4
vs2015_runtime 14.16.27012 hf0eaf9b_2
werkzeug 0.16.1 py_0
wheel 0.34.2 py37_0
win_inet_pton 1.1.0 py37_0
wincertstore 0.2 py37_0
wrapt 1.12.1 py37he774522_1
xz 5.2.5 h62dcd97_0
yaml 0.1.7 hc54c509_2
zlib 1.2.11 h62dcd97_4
zstd 1.3.7 h508b16e_0 =============== State File ================= { "name": "original", "sessions": { "1": { "timestamp": 1591084995.354819, "no_logs": false, "pingpong": false, "loss_names": { "a": [ "face_loss" ], "b": [ "face_loss" ] }, "batchsize": 64, "iterations": 1, "config": { "learning_rate": 5e-05 } }, "2": { "timestamp": 1591093982.0619726, "no_logs": false, "pingpong": false, "loss_names": { "a": [ "face_loss" ], "b": [ "face_loss" ] }, "batchsize": 64, "iterations": 101, "config": { "learning_rate": 5e-05 } } }, "lowest_avg_loss": { "a": 0.10190289102494716, "b": 0.1120093747228384 }, "iterations": 102, "inputs": { "face_in": [ 64, 64, 3 ] }, "training_size": 256, "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 [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
User avatar
torzdf
Posts: 2649
Joined: Fri Jul 12, 2019 12:53 am
Answers: 159
Has thanked: 128 times
Been thanked: 622 times

Re: plaidml.exceptions.ResourceExhausted: Unable to allocate SVM memory

Post by torzdf »

Just checking on your GPU:

The AMD Radeon R5 (Stoney Ridge) is an integrated graphics adapter of the weaker mobile dual-core Stoney Ridge APUs. At its launch, it is being used in the AMD A9-9410 and has 3 active Compute Cores (384 shaders). Depending on the model, the maximum clock is 800 MHz. The performance can vary heavily depending on the configured TDP and the system memory. Compared to the Radeon R5 from the Bristol Ridge series, it only has 3 instead of 6 GCN cores (and is the full configuration of the Stoney Ridge chip).

Most likely your GPU is just not powerful enough to train Faceswap. Ultimately, it is running out of Memory,

You can try the lightweight model with a batch size of 2 and go from there, but if that fails, then you probably won't be able to use Faceswap on that GPU

My word is final

Locked