yolov3网络架构以及代码解析二

#! /usr/bin/env python3
# coding=utf-8
#================================================================
#   Copyright (C) 2018 * Ltd. All rights reserved.
#
#   Editor      : VIM
#   File name   : yolov3.py
#   Author      : YunYang1994
#   Created date: 2018-11-21 18:41:35
#   Description : YOLOv3: An Incremental Improvement
#
#================================================================

import tensorflow as tf
from core import common
slim = tf.contrib.slim

class darknet53(object):
    """network for performing feature extraction"""

    def __init__(self, inputs):
        self.outputs = self.forward(inputs)

    def _darknet53_block(self, inputs, filters):
        """
        implement residuals block in darknet53
        """
        # 类似于残差网络的结构，通过1*1和3*3的卷积之后将input和output相加送入下一层
        shortcut = inputs
        inputs = common._conv2d_fixed_padding(inputs, filters * 1, 1)
        inputs = common._conv2d_fixed_padding(inputs, filters * 2, 3)

        inputs = inputs + shortcut
        return inputs

    def forward(self, inputs):

        inputs = common._conv2d_fixed_padding(inputs, 32,  3, strides=1)
        inputs = common._conv2d_fixed_padding(inputs, 64,  3, strides=2)
        inputs = self._darknet53_block(inputs, 32)
        inputs = common._conv2d_fixed_padding(inputs, 128, 3, strides=2)

        for i in range(2):
            inputs = self._darknet53_block(inputs, 64)

        inputs = common._conv2d_fixed_padding(inputs, 256, 3, strides=2)

        for i in range(8):
            inputs = self._darknet53_block(inputs, 128)#27层

        route_1 = inputs
        inputs = common._conv2d_fixed_padding(inputs, 512, 3, strides=2)

        for i in range(8):
            inputs = self._darknet53_block(inputs, 256)

        route_2 = inputs
        inputs = common._conv2d_fixed_padding(inputs, 1024, 3, strides=2)

        for i in range(4):
            inputs = self._darknet53_block(inputs, 512)
        #大小分别为[52,52,256]  [26,26,512]   [13,13,1024]
        return route_1, route_2, inputs



class yolov3(object):

    def __init__(self, num_classes, anchors,
                 batch_norm_decay=0.9, leaky_relu=0.1):

        # self._ANCHORS = [[10 ,13], [16 , 30], [33 , 23],
                         # [30 ,61], [62 , 45], [59 ,119],
                         # [116,90], [156,198], [373,326]]
        self._ANCHORS = anchors
        self._BATCH_NORM_DECAY = batch_norm_decay
        self._LEAKY_RELU = leaky_relu
        self._NUM_CLASSES = num_classes
        self.feature_maps = [] # [[None, 13, 13, 255], [None, 26, 26, 255], [None, 52, 52, 255]]

    def _yolo_block(self, inputs, filters):
        inputs = common._conv2d_fixed_padding(inputs, filters * 1, 1)
        inputs = common._conv2d_fixed_padding(inputs, filters * 2, 3)
        inputs = common._conv2d_fixed_padding(inputs, filters * 1, 1)
        inputs = common._conv2d_fixed_padding(inputs, filters * 2, 3)
        inputs = common._conv2d_fixed_padding(inputs, filters * 1, 1)
        route = inputs
        inputs = common._conv2d_fixed_padding(inputs, filters * 2, 3)
        return route, inputs

    #输出[gride,gride,3*(5+80)]大小的feature map
    def _detection_layer(self, inputs, anchors):
        num_anchors = len(anchors)
        feature_map = slim.conv2d(inputs, num_anchors * (5 + self._NUM_CLASSES), 1,
                                stride=1, normalizer_fn=None,
                                activation_fn=None,
                                biases_initializer=tf.zeros_initializer())
        return feature_map

    #输入[gride,gride,3*(5+80)]大小的feature map,以及anchors，输出每个cell[7*7*1*2]左上角坐标
    #box[13*13*3*4]坐标，box置信率[13*13*3</