【tensorflow + Faster RCNN】anchor_target_layer、proposal_target_layer、proposal_layer
接在tensorflow+fasterrcnn代码理解(一):构建vgg前端和RPN网络之后,对于每张输入图像(600×800)RPN会产生17100个anchor,构建RPN后会输出4个tensor,维度如下:rpn_cls_prob:(1,38,50,18)rpn_bbox_pred:(1,38,50,36)rpn_cls_score:(1,38,50,18)rpn_cls_score_res