VGG16卷积神经网络--TensorFlow2

结果展示

loss和acc曲线

epoch = 10
acc = 92.26%

计算参数

程序

# -*- coding: utf-8 -*-
"""
Created on Tue Apr 14 2020
@author: jiollos
"""
# 导入包
import tensorflow as tf
import os
import numpy as np
from matplotlib import pyplot as plt
from tensorflow.keras.layers import Conv2D, BatchNormalization, Activation, MaxPool2D, Dropout, Flatten, Dense
from tensorflow.keras import Model
# 设置显示格式
np.set_printoptions(threshold=np.inf)

# 导入数据集
fashion = tf.keras.datasets.fashion_mnist
(x_train, y_train), (x_test, y_test) = fashion.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
print("x_train.shape", x_train.shape)
# 给数据增加一个维度，使数据和网络结构匹配
x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)  
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)
print("x_train.shape", x_train.shape)

# 构建VGG16的class
class VGG16(Model):
    def __init__(self):
        super(VGG16, self).__init__()
         
        # 13层卷积网络，越往后特征图尺寸越小，通过增加卷积核的个数，增加了特征图的深度，保持了特征的承载能力
        self.c1 = Conv2D(filters=64, kernel_size=(3, 3), padding='same')  
        self.b1 = BatchNormalization()
        self.a1 = Activation('relu') 
        
        self.c2 = Conv2D(filters=64, kernel_size=(3, 3), padding='same', )
        self.b2 = BatchNormalization() 
        self.a2 = Activation('relu')  
        self.p1 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')
        self.d1 = Dropout(0.2)  

        self.c3 = Conv2D(filters=128, kernel_size=(3, 3), padding='same')
        self.b3 = BatchNormalization()  
        self.a3 = Activation('relu')  
        
        self.c4 = Conv2D(filters=128, kernel_size=(3, 3), padding='same')
        self.b4 = BatchNormalization()  
        self.a4 = Activation('relu')  
        self.p2 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')
        self.d2 = Dropout(0.2)  

        self.c5 = Conv2D(filters=256, kernel_size=(3, 3), padding='same')
        self.b5 = BatchNormalization() 
        self.a5 = Activation('relu')  
        
        self.c6 = Conv2D(filters=256, kernel_size=(3, 3), padding='same')
        self.b6 = BatchNormalization()  
        self.a6 = Activation('relu') 
        
        self.c7 = Conv2D(filters=256, kernel_size=(3, 3), padding='same')
        self.b7 = BatchNormalization()
        self.a7 = Activation('relu')
        self.p3 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')
        self.d3 = Dropout(0.2)

        self.c8 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
        self.b8 = BatchNormalization()  
        self.a8 = Activation('relu')  
        
        self.c9 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
        self.b9 = BatchNormalization()  
        self.a9 = Activation('relu') 
        
        self.c10 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
        self.b10 = BatchNormalization()
        self.a10 = Activation('relu')
        self.p4 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')
        self.d4 = Dropout(0.2)

        self.c11 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
        self.b11 = BatchNormalization() 
        self.a11 = Activation('relu') 
        
        self.c12 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
        self.b12 = BatchNormalization()  
        self.a12 = Activation('relu')  
        
        self.c13 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
        self.b13 = BatchNormalization()
        self.a13 = Activation('relu')
        self.p5 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')
        self.d5 = Dropout(0.2)
        
        # 拉直像素
        self.flatten = Flatten()
        
        # 3个全连接层
        self.f1 = Dense(512, activation='relu')
        self.d6 = Dropout(0.2)
        
        self.f2 = Dense(512, activation='relu')
        self.d7 = Dropout(0.2)
        
        self.f3 = Dense(10, activation='softmax')

    # 前向传播
    def call(self, x):
        x = self.c1(x)
        x = self.b1(x)
        x = self.a1(x)
        x = self.c2(x)
        x = self.b2(x)
        x = self.a2(x)
        x = self.p1(x)
        x = self.d1(x)

        x = self.c3(x)
        x = self.b3(x)
        x = self.a3(x)
        x = self.c4(x)
        x = self.b4(x)
        x = self.a4(x)
        x = self.p2(x)
        x = self.d2(x)

        x = self.c5(x)
        x = self.b5(x)
        x = self.a5(x)
        x = self.c6(x)
        x = self.b6(x)
        x = self.a6(x)
        x = self.c7(x)
        x = self.b7(x)
        x = self.a7(x)
        x = self.p3(x)
        x = self.d3(x)

        x = self.c8(x)
        x = self.b8(x)
        x = self.a8(x)
        x = self.c9(x)
        x = self.b9(x)
        x = self.a9(x)
        x = self.c10(x)
        x = self.b10(x)
        x = self.a10(x)
        x = self.p4(x)
        x = self.d4(x)

        x = self.c11(x)
        x = self.b11(x)
        x = self.a11(x)
        x = self.c12(x)
        x = self.b12(x)
        x = self.a12(x)
        x = self.c13(x)
        x = self.b13(x)
        x = self.a13(x)
        x = self.p5(x)
        x = self.d5(x)

        x = self.flatten(x)
        x = self.f1(x)
        x = self.d6(x)
        x = self.f2(x)
        x = self.d7(x)
        y = self.f3(x)
        return y

# 运行
model = VGG16()

# 设置优化器/交叉熵损失函数/准确率
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

# 设置断点
checkpoint_save_path = "./checkpoint/VGG16.ckpt"
if os.path.exists(checkpoint_save_path + '.index'):
    print('-------------load the model-----------------')
    model.load_weights(checkpoint_save_path)
cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,
                                                 save_weights_only=True,
                                                 save_best_only=True)

# 执行训练
history = model.fit(x_train, y_train, batch_size=32, epochs=10, validation_data=(x_test, y_test), validation_freq=1,
                    callbacks=[cp_callback])
# 展示结果
model.summary()

# 保存权重
# print(model.trainable_variables)
file = open('./weights.txt', 'w')
for v in model.trainable_variables:
    file.write(str(v.name) + '\n')
    file.write(str(v.shape) + '\n')
    file.write(str(v.numpy()) + '\n')
file.close()

# 显示训练集和验证集的acc和loss曲线
acc = history.history['sparse_categorical_accuracy']
val_acc = history.history['val_sparse_categorical_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']

#plt.subplot(1, 2, 1)
plt.plot(acc, label='Training Accuracy')
plt.plot(val_acc, label='Validation Accuracy')
plt.title('Training and Validation Accuracy')
plt.legend()
plt.show()

#plt.subplot(1, 2, 2)
plt.plot(loss, label='Training Loss')
plt.plot(val_loss, label='Validation Loss')
plt.title('Training and Validation Loss')
plt.legend()
plt.show()