The position generated by the mask in the code does not match the paper
Mr-Da-Yang opened this issue · comments
Hello there:
The paper stated that the mask is generated by restnet50. The mask in the code is generated by bottleneck. Please check and see if it is what I described.
thank you!
Hi, thanks for commenting this!
There is an error in the paper description indeed, I have updated the README so people can know about this. Results and main idea of paper don't change :) .