8. proposal_layer_tf.py ( Faster-RCNN_TF代码解读)

8. /lib/rpn_msr/proposal_layer_tf.py

本文件实现了初步筛选proposals，具体实现思路如下（右边页是思路，左边页是备注）：

_anchors输出如下：

shifts输出如下：

anchors输出如下：

# --------------------------------------------------------
# Faster R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick and Sean Bell
# --------------------------------------------------------

import numpy as np
import yaml
from fast_rcnn.config import cfg
from generate_anchors import generate_anchors
from fast_rcnn.bbox_transform import bbox_transform_inv, clip_boxes
from fast_rcnn.nms_wrapper import nms
import pdb


DEBUG = False
"""
Outputs object detection proposals by applying estimated bounding-box
transformations to a set of regular boxes (called "anchors").
"""
#要输出估计框了
#函数输入为（rpn_cls_prob_reshape：rpn_cls_score经过R-softmax-R，rpn_bbox_pred:bbox信息预测结果）
def proposal_layer(rpn_cls_prob_reshape,rpn_bbox_pred,im_info,cfg_key,_feat_stride = [16,],anchor_scales = [8, 16, 32]):
    # Algorithm:
    #
    # for each (H, W) location i
    #   generate A anchor boxes centered on cell i
    #   apply predicted bbox deltas at cell i to each of the A