Upgrade the pytorch branch to 1.0, but fails while grad checking

ZhouYanzhao / ORN

Oriented Response Networks, in CVPR 2017

http://yzhou.work/ORN

BSD 3-Clause "New" or "Revised" License

223 stars 51 forks source link

Upgrade the pytorch branch to 1.0, but fails while grad checking #17

Open ayumiymk opened 5 years ago

ayumiymk commented 5 years ago

Thanks for sharing!

Recently, I upgrade the pytorch branch to be compatible with pytorch 1.0. When I conduct the grad check for activerotaingfilter, I failed. But the rotationinvariantencoding success. I have checked my codes many times, but still don't solve it. Do you plan to upgrade this branch to python1.0?

ayumiymk commented 5 years ago

I think I have solved this bug. It is caused by the parallel for loop.

While using the openMP for parallel computing, this line and this line can not be parallel with the '++' operator. To fix this bug, I first compute the index, and then get the absolute address via uint16 gradInputIndex = i * nInputPlane * + j * + l; T *val = gradInputData + gradInputIndex;