Open fzk19996 opened 4 years ago
@fzk19996 We haven't met this error before, but you can try a commonly-used pytorch 1.0 instead of nightly version. :)
Thank you, I have ran the code in pytorch1.0 and torch vision0.2.1 successfully. In fact, i ran the 'train_net.py' successfully before submitting the issue . But I failed to ran the 'test_net.py' and I thought it is because of the wrong version of pytorch and torchvision. Now, the RRPN_demo works fine on my computer. Thanks to your help.
At 2019-12-31 22:44:43, "mjq11302010044" notifications@github.com wrote:
@fzk19996 We haven't met this error before, but you can try a commonly-used pytorch 1.0 instead of nightly version. :)
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.
I'm using torch=1.1.0 while installing torch_sparse-0.6.7 failed with this error.
Upgrading to torch 1.4.0 with cuda10.1 works.
my pytorch vision is pytorch-nightly==1.0.0 and cuda version is 9.0. The torchvision code is cloned from https://github.com/pytorch/vision.git, and the branch is master. I think the reason is that the pytorch vision is incompatible with the pytorch vision. I have tried different torchvision installed from conda and the code have some problems to run. So please tell me the correct the version of pytorch and torchvision. Thank you!