search

jeong-tae / RACNN-pytorch

This is a third party implementation of RA-CNN in pytorch.
201 stars 63 forks source link

about apn #15

Closed narrowsnap closed 4 years ago

narrowsnap commented 5 years ago

Hi, I read your code which is cool, and run it. But the APN model which implement from the Paper is not concise and confused me.

I spend much time on thinking about it. I suddenly see the light when I read The Spatial Transformer Networks.

All the crop operate can description with a 2x3 matrix([[0.5, 0.0, 0.0], [0.0, 0.5, 0.0]]).

selection_052

M00 and M11 mean the size of crop area, M02 and M12 mean the coordinate of crop area.

selection_053

Which means we only need to train 2 parameter(M02 and M12) to find the attention area.

selection_054

And The Spatial Transformer Networks can autograd which we don't need to write the complex crop function.

I'm not finish trained The Spatial Transformer Networks when I write this text. I just want to share the stn net with you. That's wonderful!

Hope this can help you!

jeong-tae commented 5 years ago

Thank you for sharing. The reason why I implement this is only for understanding more about paper. If I can't reproduce performance same as write in the paper, which means that there is still missing to understand fully.

I know this repository become more getting interest but still busy these days. Anyway, thank you for the sharing and I will figure out the reason to reproduce this someday!