Deepstack Facial Recognition Error - 'Hardswish' object has no attribute 'inplace'

Hi all, I’m running the gpu docker version of Deepstack (gpu-2021.09.1) with a 3060 ti. As has been noted in another forum post here [GeForce RTX 3060 Ti GPU can't work], torch and torchvision must be manually updated to work with the 3060 ti, which I was able to do with the following command “pip install torch==1.10.0+cu113 torchvision==0.11.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html”.

After updating torch and torchvision, the object recognition works perfectly on my gpu; however, the facial recognition fails with “AttributeError: ‘Hardswish’ object has no attribute ‘inplace’”. The contents of the stderr log are below:

Traceback (most recent call last):

File “/app/intelligencelayer/shared/face.py”, line 307, in face
det = detector.predict(img, 0.55)
File “/app/intelligencelayer/shared/./process.py”, line 61, in predict
pred = self.model(img, augment=False)[0]
File “/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py”, line 1102, in _call_impl
return forward_call(*input, **kwargs)
File “/app/intelligencelayer/shared/./models/yolo.py”, line 149, in forward
return self.forward_once(x, profile) # single-scale inference, train
File “/app/intelligencelayer/shared/./models/yolo.py”, line 176, in forward_once
x = m(x) # run
File “/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py”, line 1102, in _call_impl
return forward_call(*input, **kwargs)
File “/app/intelligencelayer/shared/./models/common.py”, line 109, in forward
1,
File “/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py”, line 1102, in _call_impl
return forward_call(*input, **kwargs)
File “/app/intelligencelayer/shared/./models/common.py”, line 32, in forward
return self.act(self.bn(self.conv(x)))
File “/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py”, line 1102, in _call_impl
return forward_call(*input, **kwargs)
File “/usr/local/lib/python3.7/dist-packages/torch/nn/modules/activation.py”, line 461, in forward
return F.hardswish(input, self.inplace)
File “/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py”, line 1178, in getattr
type(self).name, name))
AttributeError: ‘Hardswish’ object has no attribute ‘inplace’

I tried to fix this with the solution proposed on github here ([https://github.com/pytorch/pytorch/issues/46971]). Unfortunately, implementing the proposed code change simply causes the python3 (deepstack) process to immediately stop running on my gpu (it drops off nvidia-smi process list). The details of the change are below:

open ~/.local/lib/python3.8/site-packages/torch/nn/modules/activation.py
‘return F.hardswish(input, self.inplace)’ replace with ‘return F.hardswish(input)’

Has anyone else experienced this error or have any ideas how to fix it? Many thanks!