Tensorflow版Faster RCNN源码解析（TFFRCNN） （14） VGGnet_test.py

本blog为github上CharlesShang/TFFRCNN版源码解析系列代码笔记

---------------个人学习笔记---------------

----------------本文作者疆--------------

------点击此处链接至博客园原文------

 

该脚本定义了测试网络和几个变量的占位符，测试阶段test.py中im_detect函数以feed_dict馈入data等图像信息，照此层层计算。（从network.py中看）各层计算时首先置空self.inputs下一层输入列表，然后将本层的输入添加进来，将本层的输出保存在self.layers字典中可供下一层取输入数据时使用

整个工程定义了许多类，类间调用逻辑顺序不明，该VGGnet_test类以何种方式被调用？

为什么rpn_cls_score在softmax前要reshape？然后再reshape回来？？？应与softmax接收的输入有关

import tensorflow as tf
from .network import Network
from ..fast_rcnn.config import cfg

# 以何种方式被调用？？？
class VGGnet_test(Network):
    # 重构了基类Network中的__init__(...)方法,则基类__init__(...)不执行
    def __init__(self, trainable=True):
        # 存储下一层的输入（列表）
        self.inputs = []
        self.data = tf.placeholder(tf.float32, shape=[None, None, None, 3])
        self.im_info = tf.placeholder(tf.float32, shape=[None, 3])
        self.keep_prob = tf.placeholder(tf.float32)
        # 存储各层的输出（字典）
        self.layers = dict({'data': self.data, 'im_info': self.im_info})
        self.trainable = trainable
        self.setup()

    # 重构了基类Network中的setup方法
    def setup(self):
        #n_classes = 21  #2018.1.30
        n_classes = cfg.NCLASSES
        # anchor_scales = [8, 16, 32]
        anchor_scales = cfg.ANCHOR_SCALES
        _feat_stride = [16, ]

        # 各层间运算机制可见network.py中代码理解，需要理解装饰器
        # conv1_1、conv1_2、conv2_1、conv2_2参数（在训练阶段）均不更新
        (self.feed('data')
         .conv(3, 3, 64, 1, 1, name='conv1_1', trainable=False)
         .conv(3, 3, 64, 1, 1, name='conv1_2', trainable=False)
         .max_pool(2, 2, 2, 2, padding='VALID', name='pool1')
         .conv(3, 3, 128, 1, 1, name='conv2_1', trainable=False)
         .conv(3, 3, 128, 1, 1, name='conv2_2', trainable=False)
         .max_pool(2, 2, 2, 2, padding='VALID', name='pool2')
         .conv(3, 3, 256, 1, 1, name='conv3_1')
         .conv(3, 3, 256, 1, 1, name='conv3_2')
         .conv(3, 3, 256, 1, 1, name='conv3_3')
         .max_pool(2, 2, 2, 2, padding='VALID', name='pool3')
         .conv(3, 3, 512, 1, 1, name='conv4_1')
         .conv(3, 3, 512, 1, 1, name='conv4_2')
         .conv(3, 3, 512, 1, 1, name='conv4_3')
         .max_pool(2, 2, 2, 2, padding='VALID', name='pool4')
         .conv(3, 3, 512, 1, 1, name='conv5_1')
         .conv(3, 3, 512, 1, 1, name='conv5_2')
         .conv(3, 3, 512, 1, 1, name='conv5_3'))

        # RPN
        (self.feed('conv5_3')
         .conv(3, 3, 512, 1, 1, name='rpn_conv/3x3')
        # 是/不是 fg的score
         .conv(1, 1, len(anchor_scales) * 3 * 2, 1, 1, padding='VALID', relu=False, name='rpn_cls_score'))
        (self.feed('rpn_conv/3x3')
        # ahchor的回归值
         .conv(1, 1, len(anchor_scales) * 3 * 4, 1, 1, padding='VALID', relu=False, name='rpn_bbox_pred'))

        #  shape is (1, H, W, Ax2) -> (1, H, WxA, 2)  reshape和softmax处理
        (self.feed('rpn_cls_score')
         .spatial_reshape_layer(2, name='rpn_cls_score_reshape')
         .spatial_softmax(name='rpn_cls_prob'))

        # shape is (1, H, WxA, 2) -> (1, H, W, Ax2)  reshape处理
        # 为什么softmax前要reshape？然后再reshape回来？？？应与softmax接收的输入有关
        (self.feed('rpn_cls_prob')
         .spatial_reshape_layer(len(anchor_scales) * 3 * 2, name='rpn_cls_prob_reshape'))

        (self.feed('rpn_cls_prob_reshape', 'rpn_bbox_pred', 'im_info'
        # 回归后并经过一些后处理得到的proposal，见proposal_layer_tf.py
        # 默认_feat_stride = [16, ]、anchor_scales = cfg.ANCHOR_SCALES = [8, 16, 32]、TEST模式
         .proposal_layer(_feat_stride, anchor_scales, 'TEST', name='rois'))

        # RCNN subnet
        (self.feed('conv5_3', 'rois')
         .roi_pool(7, 7, 1.0 / 16, name='pool_5')
         .fc(4096, name='fc6')
         .fc(4096, name='fc7')
        # score经过softmax后称为prob
         .fc(n_classes, relu=False, name='cls_score')
         .softmax(name='cls_prob'))

        (self.feed('fc7')
         .fc(n_classes * 4, relu=False, name='bbox_pred'))