-
Notifications
You must be signed in to change notification settings - Fork 1.4k
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
fix bug in roi pooling forwarding with cpu #1273
Conversation
Thank you for your PR. |
Unfortunately I am not familiar with software testing or software engineering. It seems that roi pooling already has the test: https://github.com/apple2373/chainer/blob/c4b5082e3b0d2973152022aecefb07486b806f5e/tests/chainer_tests/functions_tests/pooling_tests/test_roi_pooling_2d.py I want to ask inputs from @wkentaro who is the developer of this layer. I guess this is the easy mistake to understand for him. |
The code looks good to me. |
I came across the same error. @apple2373 As for the test, how about modifying this line from N = 4 to N = 3 here?: pooling_tests/test_roi_pooling_2d.py#L17 |
mitmul's idea looks good for testing this PR. |
I really do not know about software testing. Is it ok just to modify the test_roi_pooling_2d.py as mitmul mentioned, and add it to this PR? |
Yes. You can add commits into fix_roi_pooling_cpu branch, then this PR is automatically updated. |
I did it. |
Added test failed. |
I modified cpu backward in the same way. |
Thank you. |
I am not sure what is going on but the test will end up "RuntimeError: CUDA environment is not correctly set up". Maybe test cannot be run only with CPU. I'll try to run on GPU server later. |
You can run tests only on cpu by giving |
Thank you. I was able to reproduce test failure on my laptop, but I do not think I can fix it because I do not fully understand the implementation. |
I fixed the bug and open PR #1352. |
fix bug in roi pooling forwarding with cpu (continued from #1273)
Recover StandardUpdater converter backward compatibility
I implemented fast r-cnn https://github.com/apple2373/chainer-simple-fast-rnn, and realized roi pooling with cpu does not work. It always outputs only one roi when forwarding. I just copied two lines from GPU implementation. Also I am not sure backward function is also wrong or not because I only use forwarding now.