Faceswap Forum

I was training the other day and it was about 6hrs in then it cut out. and ever since then I haven't been able to train or convert. I have tried uninstalling and reinstalling mini conda and face swap. I use AMD. I tried CPU only as well didn't change anything. Please help!

Also I tried to post the crash report and couldn't figure out how lol.

Loading...
Setting Faceswap backend to AMD
03/02/2021 10:45:59 INFO Log level set to: INFO
03/02/2021 10:45:59 INFO Setting up for PlaidML
03/02/2021 10:45:59 INFO Using GPU(s): ['Advanced Micro Devices, Inc. - Ellesmere (experimental)', 'Advanced Micro Devices, Inc. - Ellesmere (supported)']
03/02/2021 10:45:59 INFO Successfully set up for PlaidML

03/02/2021 10:46:02 INFO Reading alignments from: 'C:\Users\manns\Desktop\FaceSwap1\Proj4\Proj4_alignments.fsa'
03/02/2021 10:46:02 INFO Loading Writer from Ffmpeg plugin...

Using plaidml.keras.backend backend.
03/02/2021 10:46:03 INFO Using configuration saved in state file
03/02/2021 10:46:03 INFO Opening device "opencl_amd_ellesmere.0"
03/02/2021 10:46:06 ERROR Got Exception on main handler:
Traceback (most recent call last):
File "C:\Users\manns\Desktop\faceswap\lib\cli\launcher.py", line 181, in execute_script
process = script(arguments)
File "C:\Users\manns\Desktop\faceswap\scripts\convert.py", line 65, in init
self.predictor = Predict(self.disk_io.load_queue, self.queue_size, arguments)
File "C:\Users\manns\Desktop\faceswap\scripts\convert.py", line 661, in init
self.model = self._load_model()
File "C:\Users\manns\Desktop\faceswap\scripts\convert.py", line 746, in load_model
model.build()
File "C:\Users\manns\Desktop\faceswap\plugins\train\model\_base.py", line 258, in build
model = self.io._load() # pylint:disable=protected-access
File "C:\Users\manns\Desktop\faceswap\plugins\train\model\_base.py", line 520, in load
model = load_model(self.filename, compile=False)
File "C:\Users\manns\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\manns\MiniConda3\envs\faceswap\lib\site-packages\keras\engine\saving.py", line 249, in deserialize_model
layer_weights = model_weights_group[name]
File "C:\Users\manns\MiniConda3\envs\faceswap\lib\site-packages\keras\utils\io_utils.py", line 303, in getitem
val = H5Dict(self.data.create_group(attr))
File "C:\Users\manns\MiniConda3\envs\faceswap\lib\site-packages\h5py\_hl\group.py", line 68, in create_group
gid = h5g.create(self.id, name, lcpl=lcpl, gcpl=gcpl)
File "h5py\_objects.pyx", line 54, in h5py.objects.with_phil.wrapper
File "h5py\_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py\h5g.pyx", line 161, in h5py.h5g.create
ValueError: Unable to create group (no write intent on file)
03/02/2021 10:46:06 CRITICAL An unexpected crash has occurred. Crash report written to 'C:\Users\manns\Desktop\faceswap\crash_report.2021.03.02.104604302405.log'. You MUST provide this file if seeking assistance. Please verify you are running the latest version of faceswap before reporting

Process exited.

Without the crash report I can't be sure, but this looks like the model file has corrupted. Make a copy and try the restore tool to see if that fixes it. Otherwise, post your crash log to a cloud service and share the link it here.

https://github.com/Jmanns356/Error-Code

hopefully that is done correctly lol.

you think its a corrupt model file even though I tried to train other projects and those didnt work either?

So that did fix the converting problem! Thank you!

I'm confused how it fixed the training issue though lol since I even tried other projects.

The other errors you were getting weren't related to the first error. Looks like you were training and had a face that had no alignments. Glad the restore fixed it for you.