（Windows10）Tensorflow下实现FCN

结果是在8GB 1070上训练大约10~11个小时后获得的。

FCN-TensorFlow完整代码Github：https://github.com/EternityZY/FCN-TensorFlow.git

一：准备工作

1.然后下载VGG网络的权重参数，下载好后的文件路径为./Model_zoo/imagenet-vgg-verydeep-19.mat.

MODEL_URL =  'http://www.vlfeat.org/matconvnet/models/beta16/imagenet-vgg-verydeep-19.mat'

2.数据集下载，也可把自己数据集放入，代替./Data_zoo/MIT_SceneParsing/ADEChallengeData2016文件

DATA_URL =  'http://data.csail.mit.edu/places/ADEchallenge/ADEChallengeData2016.zip'

二：开始训练
注意：

• 训练模型只需执行python FCN.py

• 修改学习率1e-5 甚至更小 否则loss会一直在3左右浮动

• debug标志可以在训练期间设置，以添加关于激活函数，梯度，变量等的信息。

• 训练时把FCN.py中的全局变量mode改为“train”，运行该文件，测试时修改测试函数里的图片地址，并把mode改为“test”运行即可

• 

代码的实现有四个python文件，分别是FCN.py、BatchDatasetReader.py、TensorFlowUtils.py、read_MITSceneParsingData.py。将这四个文件放在一个当前目录 下，此处附上修改过后的四个文件：

FCN.py为主文件，代码如下：

from __future__ import print_function
import tensorflow as tf
import numpy as np

import TensorflowUtils as utils
import read_MITSceneParsingData as scene_parsing
import datetime
import BatchDatsetReader as dataset
from six.moves import xrange

FLAGS = tf.flags.FLAGS
#batch大小
tf.flags.DEFINE_integer("batch_size", "2", "batch size for training")
#存放存放数据集的路径，需要提前下载
tf.flags.DEFINE_string("logs_dir", "logs/", "path to logs directory")
tf.flags.DEFINE_string("data_dir", "Data_zoo/MIT_SceneParsing/", "path to dataset")
# 学习率
tf.flags.DEFINE_float("learning_rate", "1e-4", "Learning rate for Adam Optimizer")
# VGG网络参数文件，需要提前下载
tf.flags.DEFINE_string("model_dir", "Model_zoo/", "Path to vgg model mat")
tf.flags.DEFINE_bool('debug', "False", "Debug mode: True/ False")
tf.flags.DEFINE_string('mode', "train", "Mode train/ test/ visualize")

MODEL_URL = 'http://www.vlfeat.org/matconvnet/models/beta16/imagenet-vgg-verydeep-19.mat'

MAX_ITERATION = int(1e5 + 1)      # 最大迭代次数
NUM_OF_CLASSESS = 151                # 类的个数
IMAGE_SIZE = 224                     # 图像尺寸

#vggnet函数
# 根据载入的权重建立原始的 VGGNet 的网络
def vgg_net(weights, image):
    layers = (
        'conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1',

        'conv2_1', 'relu2_1', 'conv2_2', 'relu2_2', 'pool2',

        'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2', 'conv3_3',
        'relu3_3', 'conv3_4', 'relu3_4', 'pool3',

        'conv4_1', 'relu4_1', 'conv4_2', 'relu4_2', 'conv4_3',
        'relu4_3', 'conv4_4', 'relu4_4', 'pool4',

        'conv5_1', 'relu5_1', 'conv5_2', 'relu5_2', 'conv5_3',
        'relu5_3', 'conv5_4', 'relu5_4'
    )

    net = {}
    current = image
    for i, name in enumerate(layers):
        kind = name[:4]
        if kind == 'conv':
            kernels, bias = weights[i][0][0][0][0]
            # matconvnet: weights are [width, height, in_channels, out_channels]
            # tensorflow: weights are [height, width, in_channels, out_channels]
            kernels = utils.get_variable(np.transpose(kernels, (1, 0, 2, 3)), name=name + "_w")
            bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
            current = utils.conv2d_basic(current, kernels, bias)
        elif kind == 'relu':
            current = tf.nn.relu(current, name=name)
            if FLAGS.debug:
                utils.add_activation_summary(current)
        elif kind == 'pool':
            current = utils.avg_pool_2x2(current)
        net[name] = current

    return net

# inference函数，FCN的网络结构定义，网络中用到的参数是迁移VGG训练好的参数
def inference(image, keep_prob):    #输入图像和dropout值
    """
    Semantic segmentation network definition
    :param image: input image. Should have values in range 0-255
    :param keep_prob:
    :return:
    """
    # 加载模型数据，获得标准化均值
    print("setting up vgg initialized conv layers ...")
    model_data = utils.get_model_data(FLAGS.model_dir, MODEL_URL)

    mean = model_data['normalization'][0][0][0]   # 通过字典获取mean值,vgg模型参数里有normaliza这个字典，三个0用来去虚维找到mean
    mean_pixel = np.mean(mean, axis=(0, 1))

    weights = np.squeeze(model_data['layers'])# 从数组的形状中删除单维度条目，获得vgg权重

    # 图像预处理
    processed_image = utils.process_image(image, mean_pixel) # 图像减平均值实现标准化
    print("预处理后的图像:", np.shape(processed_image))

    with tf.variable_scope("inference"):
        # 建立原始的VGGNet-19网络
        print("开始建立VGG网络：")
        image_net = vgg_net(weights, processed_image)
        # 在VGGNet-19之后添加 一个池化层和三个卷积层
        conv_final_layer = image_net["conv5_3"]
        print("VGG处理后的图像：", np.shape(conv_final_layer))

        pool5 = utils.max_pool_2x2(conv_final_layer)

        W6 = utils.weight_variable([7, 7, 512, 4096], name="W6")
        b6 = utils.bias_variable([4096], name="b6")
        conv6 = utils.conv2d_basic(pool5, W6, b6)
        relu6 = tf.nn.relu(conv6, name="relu6")
        if FLAGS.debug:
            utils.add_activation_summary(relu6)
        relu_dropout6 = tf.nn.dropout(relu6, keep_prob=keep_prob)

        W7 = utils.weight_variable([1, 1, 4096, 4096], name="W7")
        b7 = utils.bias_variabl