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.

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

Install from Pytorch@commitfd25a2a #52

Open
gaowu9595 opened this issue Apr 14, 2019 · 7 comments
Open

Install from Pytorch@commitfd25a2a #52

gaowu9595 opened this issue Apr 14, 2019 · 7 comments

Comments

@gaowu9595
Copy link

Hi,
I followed the tutorial to install pytorch@commit fd25a2a from the source. But when I run the following command to install the third/party:
git submodule update --init --recursive

Then the following error message appeared:
remote: Repository not found.
fatal: repository 'https://github.com/NervanaSystems/nervanagpu.git/' not found
fatal: clone of 'https://github.com/NervanaSystems/nervanagpu.git' into submodule path 'third_party/nervanagpu' failed

That means the Repository has gone, and I can't install the pytorch from source.
Do you know how to solve it?

@emma-sjwang
Copy link

#17

@MSC19950601
Copy link

same problems!

@junfu1115
Copy link
Owner

I recommend Zhang Hang's repo to install torch and torch-encoding

@MendelXu
Copy link

MendelXu commented May 4, 2019

@junfu1115 Does it mean pytorch1.0 is also ok for result reproducing? I have tried to reproduce the result with torch=0.4.1, however, the result is 78.94, which is 1 point lower than yours. Thanks a lot.

@wuusn
Copy link

wuusn commented May 17, 2019

@MendelXu same torch=0.4.1 here, got mIoU 0.7991

@MendelXu
Copy link

@wuusn This is really weird...Even after I change to pytorch1.0, the mIOU is only 0.795, which is still lower than yours.

@lyn-rgb
Copy link

lyn-rgb commented Aug 12, 2019

@MendelXu Hi, I am reproducing the result too. I just got 0.7730 with PyTorch 1.0 on the val set. I notice that the result of the 15th category is very lower than the provided model by the author, 0.4574 vs 0.8530. I wonder what caused this, can you tell me your system envs and any special settings (Like dataset processing)? Thanks a lot.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

7 participants