使用VGG-19模型训练自己的数据集_vgg19模型

作者：从前慢现在也慢 | 2024-03-30 13:32:00

踩

vgg19模型

前言：

上一节介绍的图像识别中一个经典的模型AlexNet，今天介绍的是图像识别领域另一个经典的模型VGG-19。VGG-19是由牛津大学的Oxford Visual Geometry Group实验室发明的。因为不像是AlexNet是由Alex一个人完成的。所以这个模型就按照实验室的名称的缩写命名。VGG-19和AlexNet的整体架构是相似的，只是在AlexNet进行了一些改进，具体的有。

第一： VGG16相比AlexNet的一个改进是采用连续的几个3x3的卷积核代替AlexNet中的较大卷积核（11x11，7x7，5x5）

第二： VGGNet的结构非常简洁，整个网络都使用了同样大小的卷积核尺寸（3x3）和最大池化尺寸（2x2）

VGG-19的架构图：

首先让我们看一下VGG的发展历程，第三行表示VGG不同版本的卷积层数，从11层到13再到16最后达到19层。

首先同样是本程序的主程序：

和上一节的AlexNet几乎一毛一样。所以只把代码公布一下，就不做解释了。


# -*- coding: utf-8 -*-
# @Time    : 2019/7/2 16:07
# @Author  : YYLin
# @Email   : 854280599@qq.com
# @File    : VGG_19_Train.py
# 定义一些模型中所需要的参数
from VGG_19 import VGG19
import tensorflow as tf
import os
import cv2
import numpy as np
from keras.utils import to_categorical
 
batch_size = 64
img_high = 100
img_width = 100
Channel = 3
label = 9
 
# 定义输入图像的占位符
inputs = tf.placeholder(tf.float32, [batch_size, img_high, img_width, Channel], name='inputs')
y = tf.placeholder(dtype=tf.float32, shape=[batch_size, label], name='label')
keep_prob = tf.placeholder("float")
is_train = tf.placeholder(tf.bool)
 
model = VGG19(inputs, keep_prob, label)
score = model.fc8
softmax_result = tf.nn.softmax(score)
 
# 定义损失函数 以及相对应的优化器
cross_entropy = -tf.reduce_sum(y*tf.log(softmax_result))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
 
# 显示最后预测的结果
correct_prediction = tf.equal(tf.argmax(softmax_result, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
 
 
# 现在的我只需要加载图像和对应的label即可 不需要加载text中的内容
def load_satetile_image(batch_size=128, dataset='train'):
    img_list = []
    label_list = []
    dir_counter = 0
 
    if dataset == 'train':
        path = '../Dataset/baidu/train_image/train'
 
        # 对路径下的所有子文件夹中的所有jpg文件进行读取并存入到一个list中
        for child_dir in os.listdir(path):
            child_path = os.path.join(path, child_dir)
            for dir_image in os.listdir(child_path):
                img = cv2.imread(os.path.join(child_path, dir_image))
                img = img / 255.0
                img_list.append(img)
                label_list.append(dir_counter)
 
            dir_counter += 1
    else:
        path = '../Dataset/baidu/valid_image/valid'
 
        # 对路径下的所有子文件夹中的所有jpg文件进行读取并存入到一个list中
        for child_dir in os.listdir(path):
            child_path = os.path.join(path, child_dir)
            for dir_image in os.listdir(child_path):
                img = cv2.imread(os.path.join(child_path, dir_image))
                img = img / 255.0
                img_list.append(img)
                label_list.append(dir_counter)
 
            dir_counter += 1
 
    # 返回的img_list转成了 np.array的格式
    X_train = np.array(img_list)
    Y_train = to_categorical(label_list, 9)
    # print('to_categorical之后Y_train的类型和形状:', type(Y_train), Y_train.shape)
 
    # 加载数据的时候 重新排序
    data_index = np.arange(X_train.shape[0])
    np.random.shuffle(data_index)
    data_index = data_index[:batch_size]
    x_batch = X_train[data_index, :, :, :]
    y_batch = Y_train[data_index, :]
 
    return x_batch, y_batch
 
 
# 开始feed 数据并且训练数据
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(500000//batch_size):
        # 加载训练集和验证集
        img, img_label = load_satetile_image(batch_size, dataset='train')
        img_valid, img_valid_label = load_satetile_image(batch_size, dataset='vaild')
        # print('使用 mnist.train.next_batch加载的数据集形状', img.shape, type(img))
 
        # print('模型使用的是dropout的模型')
        dropout_rate = 0.5
        # print('经过 tf.reshape之后数据的形状以及类型是:', img.shape, type(img))
        if i % 20 == 0:
            train_accuracy = accuracy.eval(feed_dict={inputs: img, y: img_label, keep_prob: dropout_rate})
            print("step %d, training accuracy %g" % (i, train_accuracy))
        train_step.run(feed_dict={inputs: img, y: img_label, keep_prob: dropout_rate})
 
        # 输出验证集上的结果
        if i % 50 == 0:
            dropout_rate = 1
            valid_socre = accuracy.eval(feed_dict={inputs: img_valid, y: img_valid_label, keep_prob: dropout_rate})
            print("step %d, valid accuracy %g" % (i, valid_socre))

本节的核心代码 VGG-19：

从图中我们可以看到VGG-19有16个卷积层，卷积层的通道数分别是64、128、256、512。最后有三个全连接层通道数分别是4096，4096，1000。

第一： VGG-19所有的卷积核大小都是 3 * 3，步长为1 * 1。代码中满足要求

第二： VGG-19所有最大池化层的卷积核大小为2 * 2，步长为1 * 1 代码中满足要求

第三：根据上图查看一下每层卷积操作的通道数是否与代码对应显然代码满足要求。

第四：在第一节的时候我们向模型中增加一些优化技巧，我们发现使用batch normalize的话，能够极大的提高模型的准确率。但是VGG-19中并没有增加。尝试增加batch normalize。而且也没有使用一些激活函数，所以说这个模型可以尝试的优化方案还是很多的。


# -*- coding: utf-8 -*-
# @Time    : 2019/7/2 8:18
# @Author  : YYLin
# @Email   : 854280599@qq.com
# @File    : VGG_19.py
# 本模型为VGG-19参考代码链接
import tensorflow as tf
 
 
def maxPoolLayer(x, kHeight, kWidth, strideX, strideY, name, padding="SAME"):
    return tf.nn.max_pool(x, ksize=[1, kHeight, kWidth, 1],
                          strides=[1, strideX, strideY, 1], padding=padding, name=name)
 
 
def dropout(x, keepPro, name=None):
    return tf.nn.dropout(x, keepPro, name)
 
 
def fcLayer(x, inputD, outputD, reluFlag, name):
    with tf.variable_scope(name) as scope:
        w = tf.get_variable("w", shape=[inputD, outputD], dtype="float")
        b = tf.get_variable("b", [outputD], dtype="float")
        out = tf.nn.xw_plus_b(x, w, b, name=scope.name)
        if reluFlag:
            return tf.nn.relu(out)
        else:
            return out
 
 
def convLayer(x, kHeight, kWidth, strideX, strideY, featureNum, name, padding = "SAME"):
 
    channel = int(x.get_shape()[-1])
    with tf.variable_scope(name) as scope:
        w = tf.get_variable("w", shape=[kHeight, kWidth, channel, featureNum])
        b = tf.get_variable("b", shape=[featureNum])
        featureMap = tf.nn.conv2d(x, w, strides=[1, strideY, strideX, 1], padding=padding)
        out = tf.nn.bias_add(featureMap, b)
        return tf.nn.relu(tf.reshape(out, featureMap.get_shape().as_list()), name=scope.name)
 
 
class VGG19(object):
    def __init__(self, x, keepPro, classNum):
        self.X = x
        self.KEEPPRO = keepPro
        self.CLASSNUM = classNum
        self.begin_VGG_19()
 
    def begin_VGG_19(self):
        """build model"""
        conv1_1 = convLayer(self.X, 3, 3, 1, 1, 64, "conv1_1" )
        conv1_2 = convLayer(conv1_1, 3, 3, 1, 1, 64, "conv1_2")
        pool1 = maxPoolLayer(conv1_2, 2, 2, 2, 2, "pool1")
 
        conv2_1 = convLayer(pool1, 3, 3, 1, 1, 128, "conv2_1")
        conv2_2 = convLayer(conv2_1, 3, 3, 1, 1, 128, "conv2_2")
        pool2 = maxPoolLayer(conv2_2, 2, 2, 2, 2, "pool2")
 
        conv3_1 = convLayer(pool2, 3, 3, 1, 1, 256, "conv3_1")
        conv3_2 = convLayer(conv3_1, 3, 3, 1, 1, 256, "conv3_2")
        conv3_3 = convLayer(conv3_2, 3, 3, 1, 1, 256, "conv3_3")
        conv3_4 = convLayer(conv3_3, 3, 3, 1, 1, 256, "conv3_4")
        pool3 = maxPoolLayer(conv3_4, 2, 2, 2, 2, "pool3")
 
        conv4_1 = convLayer(pool3, 3, 3, 1, 1, 512, "conv4_1")
        conv4_2 = convLayer(conv4_1, 3, 3, 1, 1, 512, "conv4_2")
        conv4_3 = convLayer(conv4_2, 3, 3, 1, 1, 512, "conv4_3")
        conv4_4 = convLayer(conv4_3, 3, 3, 1, 1, 512, "conv4_4")
        pool4 = maxPoolLayer(conv4_4, 2, 2, 2, 2, "pool4")
 
        conv5_1 = convLayer(pool4, 3, 3, 1, 1, 512, "conv5_1")
        conv5_2 = convLayer(conv5_1, 3, 3, 1, 1, 512, "conv5_2")
        conv5_3 = convLayer(conv5_2, 3, 3, 1, 1, 512, "conv5_3")
        conv5_4 = convLayer(conv5_3, 3, 3, 1, 1, 512, "conv5_4")
        pool5 = maxPoolLayer(conv5_4, 2, 2, 2, 2, "pool5")
        print('最后一层卷积层的形状是:', pool5.shape)
 
        fcIn = tf.reshape(pool5, [-1, 4*4*512])
        fc6 = fcLayer(fcIn, 4*4*512, 4096, True, "fc6")
        dropout1 = dropout(fc6, self.KEEPPRO)
 
        fc7 = fcLayer(dropout1, 4096, 4096, True, "fc7")
        dropout2 = dropout(fc7, self.KEEPPRO)
 
        self.fc8 = fcLayer(dropout2, 4096, self.CLASSNUM, True, "fc8")

VGG-19增加batch normalize：亲测是可以使用的，但是需要将batch_size修改成32不然GPU显存溢出


# -*- coding: utf-8 -*-
# @Time    : 2019/7/2 16:57
# @Author  : YYLin
# @Email   : 854280599@qq.com
# @File    : VGG_19_BN.py
import tensorflow as tf
 
 
# 相对于第一个版本 增加的批量正则化 2019 7 2
def bn(x, is_training):
    return tf.layers.batch_normalization(x, training=is_training)
 
 
def maxPoolLayer(x, kHeight, kWidth, strideX, strideY, name, padding="SAME"):
    return tf.nn.max_pool(x, ksize=[1, kHeight, kWidth, 1],
                          strides=[1, strideX, strideY, 1], padding=padding, name=name)
 
 
def dropout(x, keepPro, name=None):
    return tf.nn.dropout(x, keepPro, name)
 
 
def fcLayer(x, inputD, outputD, reluFlag, name):
    with tf.variable_scope(name) as scope:
        w = tf.get_variable("w", shape=[inputD, outputD], dtype="float")
        b = tf.get_variable("b", [outputD], dtype="float")
        out = tf.nn.xw_plus_b(x, w, b, name=scope.name)
        if reluFlag:
            return tf.nn.relu(out)
        else:
            return out
 
 
def convLayer(x, kHeight, kWidth, strideX, strideY, featureNum, name, padding = "SAME"):
 
    channel = int(x.get_shape()[-1])
    with tf.variable_scope(name) as scope:
        w = tf.get_variable("w", shape=[kHeight, kWidth, channel, featureNum])
        b = tf.get_variable("b", shape=[featureNum])
        featureMap = tf.nn.conv2d(x, w, strides=[1, strideY, strideX, 1], padding=padding)
        out = tf.nn.bias_add(featureMap, b)
        return tf.nn.relu(tf.reshape(out, featureMap.get_shape().as_list()), name=scope.name)
 
 
class VGG19(object):
    def __init__(self, x, keepPro, classNum, is_training):
        self.X = x
        self.KEEPPRO = keepPro
        self.CLASSNUM = classNum
        self.is_training = is_training
        self.begin_VGG_19()
 
    def begin_VGG_19(self):
        """build model"""
        conv1_1 = convLayer(self.X, 3, 3, 1, 1, 64, "conv1_1" )
        conv1_1 = bn(conv1_1, self.is_training)
 
        conv1_2 = convLayer(conv1_1, 3, 3, 1, 1, 64, "conv1_2")
        conv1_2 = bn(conv1_2, self.is_training)
        pool1 = maxPoolLayer(conv1_2, 2, 2, 2, 2, "pool1")
 
        conv2_1 = convLayer(pool1, 3, 3, 1, 1, 128, "conv2_1")
        conv2_1 = bn(conv2_1, self.is_training)
 
        conv2_2 = convLayer(conv2_1, 3, 3, 1, 1, 128, "conv2_2")
        conv2_2 = bn(conv2_2, self.is_training)
        pool2 = maxPoolLayer(conv2_2, 2, 2, 2, 2, "pool2")
 
        conv3_1 = convLayer(pool2, 3, 3, 1, 1, 256, "conv3_1")
        conv3_1 = bn(conv3_1, self.is_training)
 
        conv3_2 = convLayer(conv3_1, 3, 3, 1, 1, 256, "conv3_2")
        conv3_2 = bn(conv3_2, self.is_training)
 
        conv3_3 = convLayer(conv3_2, 3, 3, 1, 1, 256, "conv3_3")
        conv3_3 = bn(conv3_3, self.is_training)
 
        conv3_4 = convLayer(conv3_3, 3, 3, 1, 1, 256, "conv3_4")
        conv3_4 = bn(conv3_4, self.is_training)
        pool3 = maxPoolLayer(conv3_4, 2, 2, 2, 2, "pool3")
 
        conv4_1 = convLayer(pool3, 3, 3, 1, 1, 512, "conv4_1")
        conv4_1 = bn(conv4_1, self.is_training)
 
        conv4_2 = convLayer(conv4_1, 3, 3, 1, 1, 512, "conv4_2")
        conv4_2 = bn(conv4_2, self.is_training)
        
        conv4_3 = convLayer(conv4_2, 3, 3, 1, 1, 512, "conv4_3")
        conv4_3 = bn(conv4_3, self.is_training)
        
        conv4_4 = convLayer(conv4_3, 3, 3, 1, 1, 512, "conv4_4")
        conv4_4 = bn(conv4_4, self.is_training)
        pool4 = maxPoolLayer(conv4_4, 2, 2, 2, 2, "pool4")
 
        conv5_1 = convLayer(pool4, 3, 3, 1, 1, 512, "conv5_1")
        conv5_1 = bn(conv5_1, self.is_training)
        
        conv5_2 = convLayer(conv5_1, 3, 3, 1, 1, 512, "conv5_2")
        conv5_2 = bn(conv5_2, self.is_training)
        
        conv5_3 = convLayer(conv5_2, 3, 3, 1, 1, 512, "conv5_3")
        conv5_3 = bn(conv5_3, self.is_training)
        
        conv5_4 = convLayer(conv5_3, 3, 3, 1, 1, 512, "conv5_4")
        conv5_4 = bn(conv5_4, self.is_training)
        
        pool5 = maxPoolLayer(conv5_4, 2, 2, 2, 2, "pool5")
        print('最后一层卷积层的形状是:', pool5.shape)
 
        fcIn = tf.reshape(pool5, [-1, 4*4*512])
        fc6 = fcLayer(fcIn, 4*4*512, 4096, True, "fc6")
        dropout1 = dropout(fc6, self.KEEPPRO)
 
        fc7 = fcLayer(dropout1, 4096, 4096, True, "fc7")
        dropout2 = dropout(fc7, self.KEEPPRO)
 
        self.fc8 = fcLayer(dropout2, 4096, self.CLASSNUM, True, "fc8")

VGG-19模型运行的结果分析：

VGG-19 增加BN之后的结果分析：

声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/从前慢现在也慢/article/detail/340852