Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

pytorch version #507

Closed
namihagi opened this issue Jul 27, 2020 · 2 comments
Closed

pytorch version #507

namihagi opened this issue Jul 27, 2020 · 2 comments

Comments

@namihagi
Copy link

namihagi commented Jul 27, 2020 •
edited
Loading

I tried some versions, but failed to train.
And I cant find information of enviroment in README.md.

which pytorch version do you use?
thank you!
@dikshaaswal
Copy link

dikshaaswal commented Jul 29, 2020 •
edited
Loading

Same problem with me.
RuntimeError: Legacy autograd function with non-static forward method is deprecated. Please use new-style autograd function with static forward method. (Example: https://pytorch.org/docs/stable/autograd.html#torch.autograd.Function)
Such error occured

@namihagi
Copy link
Author

I solved this problem myself.

I trained on the following environment.
Python 3.6
CUDA 10.0
Pytorch 1.0.0

I used the docker image, pytorch/pytorch:1.0-cuda10.0-cudnn7-devel.
And, I installed opencv-python, opencv-contrib-python and pycocotools by pip.
Finally, to follow this link, I changed some codes.

@gioipv gioipv mentioned this issue Jan 19, 2022
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@dikshaaswal @namihagi