Faster-RCNN and RPN Contribution RPN predefined bboxes(anchors) with different scales The rest is inherited from Fast RCNN RPN learns the proposals fr
在faster rcnn中会根据不同图的输入,得到不同的feature map,height, width = bottom[0].data.shape[-2:]首先得到conv5的高宽,以及gt box gt_boxes = bottom[1].data,图片信息im_info = bottom[2].data[0, :],然后计算偏移量,shift_x = np.arange(0, width) * self._feat_stride,在这里,你会发...