faster rcnn 中的 region proposal函数(proposal_layer、anchor_target_layer、proposal_target_layer)

代码地址：https://github.com/endernewton/tf-faster-rcnn 

1、首先，用初始化卷积核(9*2和9*4个)对vgg16生成的feature map(512通道)做卷积，得到没有实际意义[1]的rpn_cls_score和rpn_bbox_pred，之后再根据相应的loss反向传播，更新卷积核。rpn_cls_score是判断框是前景/背景，rpn_bbox_pred是预测bounding box和ground truth之间的偏移量delta。利用softmax函数把rpn_cls_score归一化，得到框属于前景/背景的概率，使前景/背景的概率总和等于1。feature map上面每个特征点有9个框，每个框有相应的背景/前景概率，所以rpn_cls_prob的shape是(1,?,?,18)。rpn_cls_pred通过argmax比较前景和背景的概率，判断框属于前景/背景。

RPN和RCNN共享这部分参数。

# 基础CNN网络（VGG16，ZF等）的参数使用ImageNet预训练，其他layer的参数使用期望为0、标准差为0.01的高斯分布初始化[6]
  def _region_proposal(self, net_conv, is_training, initializer):
    rpn = slim.conv2d(net_conv, cfg.RPN_CHANNELS, [3, 3], trainable=is_training, weights_initializer=initializer,
                        scope="rpn_conv/3x3")
    self._act_summaries.append(rpn)
    rpn_cls_score = slim.conv2d(rpn, self._num_anchors * 2, [1, 1], trainable=is_training,
                                weights_initializer=initializer,
                                padding='VALID', activation_fn=None, scope='rpn_cls_score')
    # change it so that the score has 2 as its channel size
    rpn_cls_score_reshape = self._reshape_layer(rpn_cls_score, 2, 'rpn_cls_score_reshape')
    rpn_cls_prob_reshape = self._softmax_layer(rpn_cls_score_reshape, "rpn_cls_prob_reshape")
    # 判断框属于前景/背景
    rpn_cls_pred = tf.argmax(tf.reshape(rpn_cls_score_reshape, [-1, 2]), axis=1, name="rpn_cls_pred")
    rpn_cls_prob = self._reshape_layer(rpn_cls_prob_