RuntimeError: Legacy autograd function with non-static forward method is deprecated.

[avani17101]

When running

python train.py --name edge2face_512 --dataroot datasets/face/ --dataset_mode face --input_nc 15 --loadSize 256 --num_D 1 --max_frames_per_gpu 2 --n_frames_total 6

I am getting this error:

I am using pytorch 1.9.0 and torchvision 0.10.0.

@note:
I tried to compile using pytorch0.4.1 but unable to compile resample2d_cuda. Even after running install.sh I get import error

import resample2d_cuda
ImportError: libc10.so: cannot open shared object file: No such file or directory

[avani17101]

@tcwang0509 @junyanz @jiaxianhua @mingyuliutw

[davidvfx07]

The solution is to downgrade PyTorch to version 1.4.0. However, I have an RTX 3080 Mobile so I require CUDA 11.1, which is not supported by PyTorch 1.4.0, so I can't downgrade. @tcwang0509 @junyanz @jiaxianhua @mingyuliutw from the comment above, any help here? Perhaps CPU?