AVOD-代码理解系列（三）

AVOD-代码理解

　 从输入到数据融合之前

    def build(self):

        # Setup input placeholders
        # 一堆的输入信息.就是给输入占个坑
        self._set_up_input_pls()

        # Setup feature extractors
        # 输入图像的featuremap
        self._set_up_feature_extractors()
        # proposal_input
        # 1*1卷积后的bev_fasturemap和img_featuremap
        bev_proposal_input = self.bev_bottleneck
        img_proposal_input = self.img_bottleneck
        # 融合参数
        fusion_mean_div_factor = 2.0

        # If both img and bev probabilites are set to 1.0, don't do
        # path drop.如果image和bev概率都设置为1.0，则不要执行路径丢弃。
        #train=0.9,test/val=1.0
        #ture!
        if not (self._path_drop_probabilities[0] ==
                self._path_drop_probabilities[1] == 1.0):
            with tf.variable_scope('rpn_path_drop'):
                #从均匀分布中输出随机值。.随机输出3个0-1之间的数
                random_values = tf.random_uniform(shape=[3],
                                                  minval=0.0,
                                                  maxval=1.0)
                #0.9,0.9.
                #不是零就是1
                img_mask, bev_mask = self.create_path_drop_masks(
                    self._path_drop_probabilities[0],
                    self._path_drop_probabilities[1],
                    random_values)
                #选择是否输入.如果mask为1 ,则输入,否则不输入
                img_proposal_input = tf.multiply(img_proposal_input,
                                                 img_mask)

                bev_proposal_input = tf.multiply(bev_proposal_input,
                                                 bev_mask)

                self.img_path_drop_mask = img_mask
                self.bev_path_drop_mask = bev_mask

                # Overwrite the division factor
                #在训练时的融合参数
                fusion_mean_div_factor = img_mask + bev_mask
        #bev和iname的featuremap的裁剪
        with tf.variable_scope('proposal_roi_pooling'):

            with tf.variable_scope('box_indices'):
                '''有点复杂'''
                def get_box_indices(boxes):
                    #list列表.[1,2,3...]
                    #看不懂