[AMD] AttributeError: '_Settings' object has no attribute 'prohibit_winograd'

The Extraction process failing on you, and you aren't getting an error back with clear instructions? 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 Extraction process. If you want to get tips, or better understand the Extract process, then you should look in the Extract Discussion forum.

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

Locked
User avatar
KBP
Posts: 5
Joined: Fri Aug 09, 2019 3:58 pm
Has thanked: 1 time

[AMD] AttributeError: '_Settings' object has no attribute 'prohibit_winograd'

Post by KBP »

I have had a similar problem however the program just hung once it displayed "Starting, this may take a while..." There was no information in the bottom right and the loading bar was just blank. I then updated after reading this and it's somehow got worse. It this time displays "Initializing Face Alignment Network..." beore giving me an error message "08/09/2019 17:08:08 INFO Opening device "opencl_amd_ellesmere.0"
08/09/2019 17:08:08 ERROR Caught exception in child process: 5704
08/09/2019 17:08:08 ERROR Traceback:"

I'm not very knowlegeable in the realm of coding so i'll give you this to see if you can figure out what's going on... Thanks.

Code: Select all

"Traceback (most recent call last):
File "C:\Users\KB\faceswap\plugins\extract\align\_base.py", line 112, in run
self.align(*args, **kwargs)
File "C:\Users\KB\faceswap\plugins\extract\align\_base.py", line 127, in align
self.initialize(*args, **kwargs)
File "C:\Users\KB\faceswap\plugins\extract\align\fan_amd.py", line 40, in initialize
raise err
File "C:\Users\KB\faceswap\plugins\extract\align\fan_amd.py", line 35, in initialize
self.model = FAN(self.model_path)
File "C:\Users\KB\faceswap\plugins\extract\align\fan_amd.py", line 258, in __init__
self.load_model()
File "C:\Users\KB\faceswap\plugins\extract\align\fan_amd.py", line 265, in load_model
custom_objects={'TorchBatchNorm2D': TorchBatchNorm2D}
File "C:\Users\KB\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\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\saving.py", line 225, in _deserialize_model
model = model_from_config(model_config, custom_objects=custom_objects)
File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\saving.py", line 458, in model_from_config
return deserialize(config, custom_objects=custom_objects)
File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\layers\__init__.py", line 55, in deserialize
printable_module_name='layer')
File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\utils\generic_utils.py", line 145, in deserialize_keras_object
list(custom_objects.items())))
File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\network.py", line 1032, in from_config
process_node(layer, node_data)
File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\network.py", line 991, in process_node
layer(unpack_singleton(input_tensors), **kwargs)
File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\base_layer.py", line 457, in __call__
output = self.call(inputs, **kwargs)
File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\layers\convolutional.py", line 171, in call
dilation_rate=self.dilation_rate)
File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\plaidml\keras\backend.py", line 567, in conv2d
return conv(x, kernel, strides, padding, data_format, dilation_rate)
File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\plaidml\keras\backend.py", line 524, in conv
winograd_allowed=not plaidml.settings.prohibit_winograd,
AttributeError: '_Settings' object has no attribute 'prohibit_winograd'
08/09/2019 17:08:11 ERROR    Got Exception on main handler:
Traceback (most recent call last):
File "C:\Users\KB\faceswap\lib\cli.py", line 125, in execute_script
process.process()
File "C:\Users\KB\faceswap\scripts\extract.py", line 62, in process
self.run_extraction()
File "C:\Users\KB\faceswap\scripts\extract.py", line 183, in run_extraction
self.extractor.launch()
File "C:\Users\KB\faceswap\plugins\extract\pipeline.py", line 171, in launch
self.launch_aligner()
File "C:\Users\KB\faceswap\plugins\extract\pipeline.py", line 206, in launch_aligner
raise ValueError("Error initializing Aligner")
ValueError: Error initializing Aligner
08/09/2019 17:08:11 CRITICAL An unexpected crash has occurred. Crash report written to 'C:\Users\KB\faceswap\crash_report.2019.08.09.170811716283.log'. Please verify you are running the latest version of faceswap before reporting"
by torzdf » Fri Aug 09, 2019 5:54 pm

Ok. This is a really strange bug that we haven't managed to get to the bottom of.

I won't go into the details, but this should fix the issue. Please confirm if it does:

Go Start > Anaconda Prompt

In the command window that opens enter the following:

Code: Select all

conda activate faceswap
pip install plaidml-keras==0.6.4

Close Anaconda Prompt and try Faceswap again.

Go to full post
Last edited by torzdf on Fri Aug 09, 2019 5:45 pm, edited 1 time in total.
Reason: Edited in code block
User avatar
bryanlyon
Site Admin
Posts: 793
Joined: Fri Jul 12, 2019 12:49 am
Answers: 44
Location: San Francisco
Has thanked: 4 times
Been thanked: 218 times
Contact:

Re: Extraction stuck on "Status: Executing - extract.py" in GUI

Post by bryanlyon »

KBP wrote: Fri Aug 09, 2019 4:18 pm

08/09/2019 17:08:11 CRITICAL An unexpected crash has occurred. Crash report written to 'C:\Users\KB\faceswap\crash_report.2019.08.09.170811716283.log'. Please verify you are running the latest version of faceswap before reporting"

We need this crash report.

However, I notice that you're using the AMD aligner. If you have an Nvidia card then you need to not check the AMD boxes. If you are using an AMD card please post that crash log.

User avatar
KBP
Posts: 5
Joined: Fri Aug 09, 2019 3:58 pm
Has thanked: 1 time

Re: Extraction stuck on "Status: Executing - extract.py" in GUI

Post by KBP »

Ah ok. It's not an attatchment option so i'll post the text...

Code: Select all

08/09/2019 17:08:07 Aligner.run     MainThread      _base           initialize                DEBUG    _base initialize Align: (PID: 5704, args: (), kwargs: {'event': <multiprocessing.synchronize.Event object at 0x0000019918BEEEF0>, 'error': <multiprocessing.synchronize.Event object at 0x000001991A5DB7B8>, 'log_init': <function set_root_logger at 0x0000019918EA5268>, 'log_queue': <AutoProxy[Queue] object, typeid 'Queue' at 0x1991ca5cc18>, 'log_level': 10, 'in_queue': <AutoProxy[Queue] object, typeid 'Queue' at 0x1991ca5cd30>, 'out_queue': <AutoProxy[Queue] object, typeid 'Queue' at 0x1991ca5cda0>})
08/09/2019 17:08:07 Aligner.run     MainThread      fan_amd         initialize                INFO     Initializing Face Alignment Network...
08/09/2019 17:08:07 Aligner.run     MainThread      fan_amd         initialize                DEBUG    fan initialize: (args: () kwargs: {'event': <multiprocessing.synchronize.Event object at 0x0000019918BEEEF0>, 'error': <multiprocessing.synchronize.Event object at 0x000001991A5DB7B8>, 'log_init': <function set_root_logger at 0x0000019918EA5268>, 'log_queue': <AutoProxy[Queue] object, typeid 'Queue' at 0x1991ca5cc18>, 'log_level': 10, 'in_queue': <AutoProxy[Queue] object, typeid 'Queue' at 0x1991ca5cd30>, 'out_queue': <AutoProxy[Queue] object, typeid 'Queue' at 0x1991ca5cda0>})
08/09/2019 17:08:07 Aligner.run     MainThread      fan_amd         load_model                VERBOSE  Initializing Face Alignment Network model (Keras version).
08/09/2019 17:08:08 Aligner.run     MainThread      library         _logger_callback          INFO     Opening device "opencl_amd_ellesmere.0"
08/09/2019 17:08:08 Aligner.run     MainThread      _base           run                       ERROR    Caught exception in child process: 5704
08/09/2019 17:08:08 Aligner.run     MainThread      _base           run                       ERROR    Traceback:
Traceback (most recent call last):
  File "C:\Users\KB\faceswap\plugins\extract\align\_base.py", line 112, in run
    self.align(*args, **kwargs)
  File "C:\Users\KB\faceswap\plugins\extract\align\_base.py", line 127, in align
    self.initialize(*args, **kwargs)
  File "C:\Users\KB\faceswap\plugins\extract\align\fan_amd.py", line 40, in initialize
    raise err
  File "C:\Users\KB\faceswap\plugins\extract\align\fan_amd.py", line 35, in initialize
    self.model = FAN(self.model_path)
  File "C:\Users\KB\faceswap\plugins\extract\align\fan_amd.py", line 258, in __init__
    self.load_model()
  File "C:\Users\KB\faceswap\plugins\extract\align\fan_amd.py", line 265, in load_model
    custom_objects={'TorchBatchNorm2D': TorchBatchNorm2D}
  File "C:\Users\KB\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\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\saving.py", line 225, in _deserialize_model
    model = model_from_config(model_config, custom_objects=custom_objects)
  File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\saving.py", line 458, in model_from_config
    return deserialize(config, custom_objects=custom_objects)
  File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\layers\__init__.py", line 55, in deserialize
    printable_module_name='layer')
  File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\utils\generic_utils.py", line 145, in deserialize_keras_object
    list(custom_objects.items())))
  File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\network.py", line 1032, in from_config
    process_node(layer, node_data)
  File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\network.py", line 991, in process_node
    layer(unpack_singleton(input_tensors), **kwargs)
  File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\base_layer.py", line 457, in __call__
    output = self.call(inputs, **kwargs)
  File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\keras\layers\convolutional.py", line 171, in call
    dilation_rate=self.dilation_rate)
  File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\plaidml\keras\backend.py", line 567, in conv2d
    return conv(x, kernel, strides, padding, data_format, dilation_rate)
  File "C:\Users\KB\MiniConda3\envs\faceswap\lib\site-packages\plaidml\keras\backend.py", line 524, in conv
    winograd_allowed=not plaidml.settings.prohibit_winograd,
AttributeError: '_Settings' object has no attribute 'prohibit_winograd'
08/09/2019 17:08:10 MainProcess     MainThread      plaidml_tools   initialize                DEBUG    PlaidML already initialized
08/09/2019 17:08:10 MainProcess     MainThread      plaidml_tools   get_supported_devices     DEBUG    [<plaidml._DeviceConfig object at 0x000001E7ECAA1EB8>]
08/09/2019 17:08:10 MainProcess     MainThread      plaidml_tools   get_all_devices           DEBUG    Experimental Devices: [<plaidml._DeviceConfig object at 0x000001E7ECAA03C8>]
08/09/2019 17:08:10 MainProcess     MainThread      plaidml_tools   get_all_devices           DEBUG    [<plaidml._DeviceConfig object at 0x000001E7ECAA03C8>, <plaidml._DeviceConfig object at 0x000001E7ECAA1EB8>]
08/09/2019 17:08:10 MainProcess     MainThread      plaidml_tools   __init__                  DEBUG    Initialized: PlaidMLStats
08/09/2019 17:08:10 MainProcess     MainThread      plaidml_tools   supported_indices         DEBUG    [1]
08/09/2019 17:08:10 MainProcess     MainThread      plaidml_tools   supported_indices         DEBUG    [1]
Traceback (most recent call last):
  File "C:\Users\KB\faceswap\lib\cli.py", line 125, in execute_script
    process.process()
  File "C:\Users\KB\faceswap\scripts\extract.py", line 62, in process
    self.run_extraction()
  File "C:\Users\KB\faceswap\scripts\extract.py", line 183, in run_extraction
    self.extractor.launch()
  File "C:\Users\KB\faceswap\plugins\extract\pipeline.py", line 171, in launch
    self.launch_aligner()
  File "C:\Users\KB\faceswap\plugins\extract\pipeline.py", line 206, in launch_aligner
    raise ValueError("Error initializing Aligner")
ValueError: Error initializing Aligner

============ System Information ============
encoding:            cp1252
git_branch:          master
git_commits:         1c29344 Bugfix: Fix extract/convert hanging when ffmpeg fails to get frame count. 7666fb6 Bugfix: Ignore config sections for trainers with no config
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. - Ellesmere (experimental), GPU_1: Advanced Micro Devices, Inc. - Ellesmere (supported)
gpu_devices_active:  GPU_0, GPU_1
gpu_driver:          ['2841.5', '2841.5']
gpu_vram:            GPU_0: 8192MB, GPU_1: 8192MB
os_machine:          AMD64
os_platform:         Windows-10-10.0.18362-SP0
os_release:          10
py_command:          C:\Users\KB\faceswap\faceswap.py extract -i C:/Users/KB/Desktop/LEWIS DF TEMPLATE.mp4 -o C:/Users/KB/Desktop/Jingle Jam 2019/deepfake/faceswap/test 1/A image -l 0.4 --serializer json -D s3fd -A fan-amd -nm hist -bt 0.0 -sz 256 -min 40 -een 1 -si 0 -amd -L INFO -gui
py_conda_version:    conda 4.7.11
py_implementation:   CPython
py_version:          3.6.9
py_virtual_env:      True
sys_cores:           4
sys_processor:       Intel64 Family 6 Model 158 Stepping 9, GenuineIntel
sys_ram:             Total: 16246MB, Available: 10559MB, Used: 5686MB, Free: 10559MB

=============== Pip Packages ===============
absl-py==0.7.1
astor==0.8.0
certifi==2019.6.16
cffi==1.12.3
cloudpickle==1.2.1
cycler==0.10.0
cytoolz==0.10.0
dask==2.2.0
decorator==4.4.0
enum34==1.1.6
fastcluster==1.1.25
ffmpy==0.2.2
gast==0.2.2
grpcio==1.16.1
h5py==2.9.0
imageio==2.5.0
imageio-ffmpeg==0.3.0
joblib==0.13.2
Keras==2.2.4
Keras-Applications==1.0.8
Keras-Preprocessing==1.1.0
kiwisolver==1.1.0
Markdown==3.1.1
matplotlib==2.2.2
mkl-fft==1.0.12
mkl-random==1.0.2
mkl-service==2.0.2
mock==3.0.5
networkx==2.3
numpy==1.16.2
nvidia-ml-py3==7.352.1
olefile==0.46
opencv-python==4.1.0.25
pathlib==1.0.1
Pillow==6.1.0
plaidml==0.6.4
plaidml-keras==0.6.3
protobuf==3.8.0
psutil==5.6.3
pycparser==2.19
pyparsing==2.4.0
pyreadline==2.1
python-dateutil==2.8.0
pytz==2019.1
PyWavelets==1.0.3
pywin32==223
PyYAML==5.1.1
scikit-image==0.15.0
scikit-learn==0.21.2
scipy==1.3.0
six==1.12.0
tensorboard==1.13.1
tensorflow==1.13.1
tensorflow-estimator==1.13.0
termcolor==1.1.0
toolz==0.10.0
toposort==1.5
tornado==6.0.3
tqdm==4.32.1
Werkzeug==0.15.4
wincertstore==0.2

============== Conda Packages ==============
# packages in environment at C:\Users\KB\MiniConda3\envs\faceswap:
#
# Name                    Version                   Build  Channel
_tflow_select             2.3.0                       mkl  
absl-py 0.7.1 py36_0
astor 0.8.0 py36_0
blas 1.0 mkl
ca-certificates 2019.5.15 0
certifi 2019.6.16 py36_1
cffi 1.12.3 pypi_0 pypi cloudpickle 1.2.1 py_0
cycler 0.10.0 py36h009560c_0
cytoolz 0.10.0 py36he774522_0
dask-core 2.2.0 py_0
decorator 4.4.0 py36_1
enum34 1.1.6 pypi_0 pypi fastcluster 1.1.25 py36h830ac7b_1000 conda-forge ffmpeg 4.1.3 h6538335_0 conda-forge ffmpy 0.2.2 pypi_0 pypi freetype 2.9.1 ha9979f8_1
gast 0.2.2 py36_0
grpcio 1.16.1 py36h351948d_1
h5py 2.9.0 py36h5e291fa_0
hdf5 1.10.4 h7ebc959_0
icc_rt 2019.0.0 h0cc432a_1
icu 58.2 ha66f8fd_1
imageio 2.5.0 py36_0
imageio-ffmpeg 0.3.0 py_0 conda-forge intel-openmp 2019.4 245
joblib 0.13.2 py36_0
jpeg 9b hb83a4c4_2
keras 2.2.4 0
keras-applications 1.0.8 py_0
keras-base 2.2.4 py36_0
keras-preprocessing 1.1.0 py_1
kiwisolver 1.1.0 py36ha925a31_0
libmklml 2019.0.5 0
libpng 1.6.37 h2a8f88b_0
libprotobuf 3.8.0 h7bd577a_0
libtiff 4.0.10 hb898794_2
markdown 3.1.1 py36_0
matplotlib 2.2.2 py36had4c4a9_2
mkl 2019.4 245
mkl-service 2.0.2 py36he774522_0
mkl_fft 1.0.12 py36h14836fe_0
mkl_random 1.0.2 py36h343c172_0
mock 3.0.5 py36_0
networkx 2.3 py_0
numpy 1.16.2 py36h19fb1c0_0
numpy-base 1.16.2 py36hc3f5095_0
nvidia-ml-py3 7.352.1 pypi_0 pypi olefile 0.46 py36_0
opencv-python 4.1.0.25 pypi_0 pypi openssl 1.1.1c he774522_1
pathlib 1.0.1 py36_1
pillow 6.1.0 py36hdc69c19_0
pip 19.1.1 py36_0
plaidml 0.6.4 pypi_0 pypi plaidml-keras 0.6.3 pypi_0 pypi protobuf 3.8.0 py36h33f27b4_0
psutil 5.6.3 py36he774522_0
pycparser 2.19 pypi_0 pypi pyparsing 2.4.0 py_0
pyqt 5.9.2 py36h6538335_2
pyreadline 2.1 py36_1
python 3.6.9 h5500b2f_0
python-dateutil 2.8.0 py36_0
pytz 2019.1 py_0
pywavelets 1.0.3 py36h8c2d366_1
pywin32 223 py36hfa6e2cd_1
pyyaml 5.1.1 py36he774522_0
qt 5.9.7 vc14h73c81de_0
scikit-image 0.15.0 py36ha925a31_0
scikit-learn 0.21.2 py36h6288b17_0
scipy 1.3.0 py36h29ff71c_0
setuptools 41.0.1 py36_0
sip 4.19.8 py36h6538335_0
six 1.12.0 py36_0
sqlite 3.29.0 he774522_0
tensorboard 1.13.1 py36h33f27b4_0
tensorflow 1.13.1 mkl_py36hd212fbe_0
tensorflow-base 1.13.1 mkl_py36hcaf7020_0
tensorflow-estimator 1.13.0 py_0
termcolor 1.1.0 py36_1
tk 8.6.8 hfa6e2cd_0
toolz 0.10.0 py_0
toposort 1.5 py_3 conda-forge tornado 6.0.3 py36he774522_0
tqdm 4.32.1 py_0
vc 14.1 h0510ff6_4
vs2015_runtime 14.15.26706 h3a45250_4
werkzeug 0.15.4 py_0
wheel 0.33.4 py36_0
wincertstore 0.2 py36h7fe50ca_0
xz 5.2.4 h2fa13f4_4
yaml 0.1.7 hc54c509_2
zlib 1.2.11 h62dcd97_3
zstd 1.3.7 h508b16e_0
Last edited by torzdf on Fri Aug 09, 2019 5:36 pm, edited 1 time in total.
Reason: Edited in code block
User avatar
torzdf
Posts: 2651
Joined: Fri Jul 12, 2019 12:53 am
Answers: 159
Has thanked: 129 times
Been thanked: 622 times

Re: [AMD] AttributeError: '_Settings' object has no attribute 'prohibit_winograd'

Post by torzdf »

Ok. This is a really strange bug that we haven't managed to get to the bottom of.

I won't go into the details, but this should fix the issue. Please confirm if it does:

Go Start > Anaconda Prompt

In the command window that opens enter the following:

Code: Select all

conda activate faceswap
pip install plaidml-keras==0.6.4

Close Anaconda Prompt and try Faceswap again.

My word is final

User avatar
KBP
Posts: 5
Joined: Fri Aug 09, 2019 3:58 pm
Has thanked: 1 time

Re: [AMD] AttributeError: '_Settings' object has no attribute 'prohibit_winograd'

Post by KBP »

Sorry for the late reply, currently in between two week long trips and so have just about had time to test this. It runs plaidml.keras.backend backend. but then switches to using the CPU. Is this intentional? Here's the code:

Code: Select all

08/18/2019 11:18:34 INFO     Log level set to: INFO
08/18/2019 11:18:34 INFO     Setting up for PlaidML
08/18/2019 11:18:39 INFO     Setting GPU to largest available supported device. If you want to override this selection, run `plaidml-setup` from the command line.
08/18/2019 11:18:39 INFO     Using GPU: ['opencl_amd_ellesmere.0', 'opencl_amd_ellesmere.0']
08/18/2019 11:18:39 INFO     Successfully set up for PlaidML
08/18/2019 11:18:43 INFO     Output Directory: C:\Users\KB\Desktop\Jingle Jam 2019\deepfake\faceswap\test 1\A image
08/18/2019 11:18:43 INFO     Input Video: C:\Users\KB\Desktop\LEWIS DF TEMPLATE.mp4
08/18/2019 11:18:43 INFO     Loading Detect from S3Fd plugin...
08/18/2019 11:18:43 INFO     Loading Align from Fan_Amd plugin...
08/18/2019 11:18:43 INFO     Starting, this may take a while...
08/18/2019 11:18:59 WARNING  FFMPEG hung while attempting to obtain the frame count. Retrying 2 of 3
08/18/2019 11:19:00 INFO     Initializing Face Alignment Network...
Using plaidml.keras.backend backend.
08/18/2019 11:19:02 INFO     Opening device "opencl_amd_ellesmere.0"INFO:plaidml:Opening device "opencl_amd_ellesmere.0"

08/18/2019 11:19:08 INFO     Initialized Face Alignment Network.
08/18/2019 11:19:09 INFO     Initializing S3FD Detector...
08/18/2019 11:19:24 WARNING  Using CPU

08/18/2019 11:19:24 INFO     Initialized S3FD Detector.
INFO:plaidml:Analyzing Ops: 1398 of 3641 operations complete
08/18/2019 11:19:30 INFO     Analyzing Ops: 1398 of 3641 operations complete
INFO:plaidml:Analyzing Ops: 3617 of 3641 operations complete
08/18/2019 11:19:32 INFO     Analyzing Ops: 3617 of 3641 operations complete

It is running by the way, just on CPU instead of GPU.

User avatar
torzdf
Posts: 2651
Joined: Fri Jul 12, 2019 12:53 am
Answers: 159
Has thanked: 129 times
Been thanked: 622 times

Re: [AMD] AttributeError: '_Settings' object has no attribute 'prohibit_winograd'

Post by torzdf »

Hello

Yes, this is correct. The aligner (FAN) is using GPU, but detector (S3FD) is on CPU.

The good news is we have just pushed an S3FD version compatible with AMD, so if you update Faceswap (https://faceswap.dev/forum/viewtopic.php?f=4&t=44) you should be able to extract purely on GPU.

Also, if the previous solution fixed your issue, please mark is as the solution. Many thanks!

My word is final

User avatar
KBP
Posts: 5
Joined: Fri Aug 09, 2019 3:58 pm
Has thanked: 1 time

Re: [AMD] AttributeError: '_Settings' object has no attribute 'prohibit_winograd'

Post by KBP »

Glad to say this fixed my issue, thank you! Just one question (as I am new to this forum) how do I mark a reply as solution?

User avatar
torzdf
Posts: 2651
Joined: Fri Jul 12, 2019 12:53 am
Answers: 159
Has thanked: 129 times
Been thanked: 622 times

Re: [AMD] AttributeError: '_Settings' object has no attribute 'prohibit_winograd'

Post by torzdf »

I think you found it! But for anyone else it is the "check" mark with the other buttons next to the avatar.

My word is final

Locked