Faster R-CNN tf版 _region_proposal函数

Faster R-CNN tf代码解析

训练阶段

_region_proposal函数

_region_proposal流程图如下：

各个变量的含义及维度如下表所示：

Name	Info	Dim
_num_anchors	多尺度多ratio anchors的数目	9
rpn	RPN特征层	n*w*h*cfg.RPN_CHANNELS
rpn_cls_score	archors分类特征	n*h*w*(9*2)
rpn_cls_score_reshape	rpn_cls_score形变	n*(h*9)*w*2
rpn_cls_prob_reshape	archors的类别概率	n*(h*9)*w*2
rpn_cls_pred	archors的类别	(n*h*9*w)*1
rpn_cls_prob	archors的类别概率	n*h*w*(9*2)
rpn_bbox_pred	archors的回归位置偏移	n*h*w*(9*4)
rois	候选ROI区域（类别+坐标）	n*256*5
roi_scores	初选（post_nms_topN）rois在rpn_cls_score中对应值	n*post_nms_topN*1

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)
    
    # anchor classification
    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')    
    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")  
    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_reshape, self._num_anchors * 2, "rpn_cls_prob")  
    
    ## bounding box regression
    rpn_bbox_pred = slim.conv2d(rpn, self._num_anchors * 4, [1, 1], trainable=is_training, weights_initializer=initializer, padding='VALID', activation_fn=None, scope='rpn_bbox_pred')
    
    if is_training:
        # output：post_nms_topN=2000个archors的位置（包括全0的batch_inds）及为1的概率
        rois, roi_scores = self._proposal_layer(rpn_cls_prob, rpn_bbox_pred, "rois")
        
        # rpn_labels：特征图中每个位置对应的是正样本、负样本还是不关注
        rpn_labels = self._anchor_target_layer(rpn_cls_score, "anchor")
        # Try to have a deterministic order for the computing graph, for reproducibility
        with tf.control_dependencies([rpn_labels]):  
        #通过post_nms_topN个archors的位置及为1（正样本）的概率得到256个rois（第一列的全0更新为每个archors对应的类别）及对应信息
            rois, _ = self._proposal_target_layer(rois, roi_scores, "rpn_rois")  
    else:
        if cfg.TEST.MODE == 'nms':
            # 每个位置的9个archors的类别概率和每个位置的9个archors的回归位置偏移得到post_nms_topN=300个archors的位置（包括全0的batch_inds）及为1的概率
            rois, _ = self._proposal_layer(rpn_cls_prob, rpn_bbox_pred, "rois")
        elif cfg.TEST.MODE == 'top':
            rois, _ = self._proposal_top_layer(rpn_cls_prob, rpn_bbox_pred, "rois")
        else:
            raise NotImplementedError

    self._predictions["rpn_cls_score"] = rpn_cls_score
    self._predictions["rpn_cls_score_reshape"] = rpn_cls_score_reshape
    self._predictions["rpn_cls_prob"] = rpn_cls_prob
    self._predictions["rpn_cls_pred"] = rpn_cls_pred
    self._predictions["rpn_bbox_pred"] = rpn_bbox_pred
    self._predictions["rois"] = rois

    return rois  # 返回256个archors的类别（第一维，训练时为每个archors的类别，测试时全0）及位置（后四维）

def _reshape_layer(self, bottom, num_dim, name):
    input_shape = tf.shape(bottom)
    with tf.variable_scope(name) as scope:
        # NHWC（TF数据格式）变成NCHW（caffe格式）
        to_caffe = tf.transpose(bottom, [0, 3, 1, 2])  
        # 1*(num_dim*9)*h*w==>1*num_dim*(9*h)*w
        reshaped = tf.reshape(to_caffe, tf.concat(axis=0, values=[[1, num_dim, -1], [input_shape[2]]])) 
        # NCHW（caffe格式）变成NHWC（TF数据格式） 1*num_dim*(9*h)*w --> 1*(9*h)*w*num_dim
        to_tf = tf.transpose(reshaped, [0, 2, 3, 1])
        return to_tf


def _softmax_layer(self, bottom, name):
    if name.startswith('rpn_cls_prob_reshape'):  
        # bottom：1*(h*9)*w*2
        input_shape = tf.shape(bottom)
        # 只保留最后一维，用于计算softmax的概率，其他的全合并：1*(h*9)*w*2==>(1*h*9*w)*2
        bottom_reshaped = tf.reshape(bottom, [-1, input_shape[-1]])  
        # 得到所有特征的概率
        reshaped_score = tf.nn.softmax(bottom_reshaped, name=name)  
        # 恢复到bottom的shape，(1*h*9*w)*2==>1*(h*9)*w*2
        return tf.reshape(reshaped_score, input_shape)   
    return tf.nn.softmax(bottom, name=name)

---

参考网址：

https://www.cnblogs.com/darkknightzh/p/10043864.html

论文：https://arxiv.org/abs/1506.01497

tf的第三方faster rcnn：https://github.com/endernewton/tf-faster-rcnn

IOU：https://www.cnblogs.com/darkknightzh/p/9043395.html