Hi, Charles, I'm going through your code for OHEM. And I found that the only difference between OHEM version and Standard FRCNN is on the build_loss() function, right? And all these modifications are implemented on sampled rois, which makes me quite confused. According to the paper and OHEM impletation on caffe, the hard examples should be selected from all rois.
Hi, Charles, I'm going through your code for OHEM. And I found that the only difference between OHEM version and Standard FRCNN is on the build_loss() function, right? And all these modifications are implemented on sampled rois, which makes me quite confused. According to the paper and OHEM impletation on caffe, the hard examples should be selected from all rois.