Open JinDouer opened 5 years ago
I also want to ask this point!
I am puzzled by this too. When I draw the bounding box on the picture, I find that the ground truth can not cover the target after the image has been cropped and resized. The original one is: after cropping and resizing:
I cannot understand these code,why the receptive field is subtracted to x2,y2, could you explain more about the reason? rois[:, 0] = cur_resize_ratio[0] rois[:, 1] = cur_resize_ratio[1] rois[:, 2] = np.maximum(rois[:,0]+1,rois[:, 2]cur_resize_ratio[0] - receptive_field) rois[:, 3] = np.maximum(rois[:,1]+1,rois[:, 3]cur_resize_ratio[1] - receptive_field) why not like this: rois[:, 0] = cur_resize_ratio[0] rois[:, 1] = cur_resize_ratio[1] rois[:, 2] = cur_resize_ratio[0] rois[:, 3] = cur_resize_ratio[1]