search

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

Will you release the caffe or pytorch code? #5

Closed soeaver closed 6 years ago

soeaver commented 6 years ago

Thanks!

ZhouYanzhao commented 6 years ago

Sure. I have already implemented a simplified version of ORN on Caffe/pyTorch (supports 1x1 or 3x3 ARFs only). If you need it, I will find some time next week to clean it up and release. Thanks for your interest!

soeaver commented 6 years ago

@ZhouYanzhao That' s very awesome! Looking forward your future work.

samson-wang commented 6 years ago

Waiting for the release for months! I've tried the torch version. It's much better than my caffe implementation. There must be something I misunderstood. Hope the official release will come out soon.

ZhouYanzhao commented 6 years ago

@samson-wang Thank you for your patience! The alpha version of Caffe/PyTorch implementation (PR #6) is released for your reference.

samson-wang commented 6 years ago

@ZhouYanzhao I've tried it. Thank you! In my test case, ORAlign is much better than the ORPooling. However, there is no ORAlign in the caffe implementation. An interesting observation. I tried to use pad:2 in conv1 instead of resizing image to 32x32. The test accuracy drops a lot. pad:1 is OK.

ZhouYanzhao commented 6 years ago

@samson-wang ORAlign is not supported in the alpha version of caffe implementation, but it should be easy for you to port it from the torch/pytorch implementation :) As for your observation, my little guess is that inappropriate padding could cause misalignment of hierarchical receptive fields.

I'll close this issue since the implementations are released. If you have more questions, feel free to: