TensorFlow学习笔记——（10）经典卷积网络
文章目录
-
-
- 一、概述
- 二、LeNet
-
- 1、网络介绍
- 2、完整代码
- 三、AlexNet
-
- 1、网络介绍
- 2、主要代码
- 四、VGGNet
-
- 1、网络介绍
- 2、主要代码
- 五、InceptionNet
-
- 1、网络介绍
- 2、完整代码
- 六、ResNet
-
- 1、网络介绍
- 2、完整代码
- 七、总结
-
一、概述
二、LeNet
1、网络介绍
卷积神经网络的开篇之作，通过共享卷积核减少了网络的参数。
在统计卷积网络层数时，一般只统计卷积计算层和全连接计算层，其余操作可以认为是卷积计算层的附属。
LeNet一共有五层网络，网络结构如下：
主要代码如下：
2、完整代码
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
# 设置打印选项，打印所有内容
np.set_printoptions(threshold=np.inf)
cifar10 = tf.keras.datasets.cifar10
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
# 搭建卷积模型
class LeNet5(Model):
def __init__(self):
super(LeNet5, self).__init__()
# 第一层卷积层
self.c1 = Conv2D(filters=6, kernel_size=(5, 5),
activation='sigmoid')
self.p1 = MaxPool2D(pool_size=(2, 2), strides=2)
# 第二层卷积层
self.c2 = Conv2D(filters=16, kernel_size=(5, 5),
activation='sigmoid')
self.p2 = MaxPool2D(pool_size=(2, 2), strides=2)
self.flatten = Flatten()
# 三层全连接层
self.f1 = Dense(120, activation='sigmoid')
self.f2 = Dense(84, activation='sigmoid')
self.f3 = Dense(10, activation='softmax')
def call(self, x):
x = self.c1(x)
x = self.p1(x)
x = self.c2(x)
x = self.p2(x)
x = self.flatten(x)
x = self.f1(x)
x = self.f2(x)
y = self.f3(x)
return y
model = LeNet5()
# 配置训练参数
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['sparse_categorical_accuracy'])
# 断点续训，保存模型
checkpoint_save_path = "./checkpoint/LeNet5.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)
# 执行训练过程
history = model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1,
callbacks=[cp_callback])
# 显示网络参数和结构
model.summary()
# 打印所有可训练参数，并存入weights文件
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()
############################################### show ###############################################
# 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.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()
三、AlexNet
1、网络介绍
使用relu激活函数，提升了训练速度，使用Dropout，缓解了过拟合。
AlexNet一共有8层网络，原论文中使用局部响应标准化LRN，在这里替换成BN。
2、主要代码
其余部分和上面LeNet一样，只是网络结构不一样。
class AlexNet8(Model):
def __init__(self):
super(AlexNet8, self).__init__()
self.c1 = Conv2D(filters=96, kernel_size=(3, 3))
self.b1 = BatchNormalization()
self.a1 = Activation('relu')
self.p1 = MaxPool2D(pool_size=(3, 3), strides=2)
self.c2 = Conv2D(filters=256, kernel_size=(3, 3))
self.b2 = BatchNormalization()
self.a2 = Activation('relu')
self.p2 = MaxPool2D(pool_size=(3, 3), strides=2)
self.c3 = Conv2D(filters=384, kernel_size=(3, 3), padding='same',
activation='relu')
self.c4 = Conv2D(filters=384, kernel_size=(3, 3), padding='same',
activation='relu')
self.c5 = Conv2D(filters=256, kernel_size=(3, 3), padding='same',
activation='relu')
self.p3 = MaxPool2D(pool_size=(3, 3), strides=2)
self.flatten = Flatten()
self.f1 = Dense(2048, activation='relu')
self.d1 = Dropout(0.5)
self.f2 = Dense(2048, activation='relu')
self.d2 = Dropout(0.5)
self.f3 = Dense(10, activation='softmax')
def call(self, x):
x = self.c1(x)
x = self.b1(x)
x = self.a1(x)
x = self.p1(x)
x = self.c2(x)
x = self.b2(x)
x = self.a2(x)
x = self.p2(x)
x = self.c3(x)
x = self.c4(x)
x = self.c5(x)
x = self.p3(x)
x = self.flatten(x)
x = self.f1(x)
x = self.d1(x)
x = self.f2(x)
x = self.d2(x)
y = self.f3(x)
return y
model = AlexNet8()
四、VGGNet
1、网络介绍
使用小尺寸卷积核，在减少参数的同时，提高了识别准确率，VGGNet网络结构工整，非常适合硬件加速。
网络结构是两次CBA-CBAPD，然后三次CBA-CBA-CBAPD. 最后是三层全连接。
卷积核的个数从64→128→256→512逐渐增加，因为越靠后，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，保持了信息的承载能力。
2、主要代码
class VGG16(Model):
def __init__(self):
super(VGG16, self).__init__()
self.c1 = Conv2D(filters=64, kernel_size=(3, 3), padding='same') # 卷积层1
self.b1 = BatchNormalization() # BN层1
self.a1 = Activation('relu') # 激活层1
self.c2 = Conv2D(filters=64, kernel_size=(3, 3), padding='same', )
self.b2 = BatchNormalization() # BN层1
self.a2 = Activation('relu') # 激活层1
self.p1 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')
self.d1 = Dropout(0.2) # dropout层
self.c3 = Conv2D(filters=128, kernel_size=(3, 3), padding='same')
self.b3 = BatchNormalization() # BN层1
self.a3 = Activation('relu') # 激活层1
self.c4 = Conv2D(filters=128, kernel_size=(3, 3), padding='same')
self.b4 = BatchNormalization() # BN层1
self.a4 = Activation('relu') # 激活层1
self.p2 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')
self.d2 = Dropout(0.2) # dropout层
self.c5 = Conv2D(filters=256, kernel_size=(3, 3), padding='same')
self.b5 = BatchNormalization() # BN层1
self.a5 = Activation('relu') # 激活层1
self.c6 = Conv2D(filters=256, kernel_size=(3, 3), padding='same')
self.b6 = BatchNormalization() # BN层1
self.a6 = Activation('relu') # 激活层1
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() # BN层1
self.a8 = Activation('relu') # 激活层1
self.c9 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
self.b9 = BatchNormalization() # BN层1
self.a9 = Activation('relu') # 激活层1
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() # BN层1
self.a11 = Activation('relu') # 激活层1
self.c12 = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
self.b12 = BatchNormalization() # BN层1
self.a12 = Activation('relu') # 激活层1
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)
self.flatten = Flatten()
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')
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
model = VGG16()
五、InceptionNet
1、网络介绍
引入了inception结构块在同一层网络内，使用不同尺寸的卷积核，提升了模型感知力，使用批标准化，缓解了梯度消失。
Inception结构块：同一层网络中使用了多个尺寸的卷积核，可以提取不同尺寸的特征，通过1×1卷积核，作用到输入特征图的每个像素点，通过设定少如输入特征图深度的1×1卷积核个数，减少了输出特征图深度，起到降维作用，减少了参数量和计算量。一个结构块包含四个分支，送到卷积连接器的特征数据尺寸相同，卷积连接器将四个分支按照深度方向堆叠在一起，构成Inception结构块的输出。
由于Inception结构块中的卷积操作均采用CBA结构（先卷积，再BN，再采用relu激活函数），所以将其定义成一个新的类ConvBNRelu，可以减少代码长度，增加可读性。
class ConvBNRelu(Model):
def __init__(self, ch, kernelsz=3, strides=1, padding='same'):
super(ConvBNRelu, self).__init__()
self.model = tf.keras.models.Sequential([
Conv2D(ch, kernelsz, strides=strides, padding=padding),
BatchNormalization(),
Activation('relu')
])
def call(self, x):
x = self.model(x, training=False) #在training=False时，BN通过整个训练集计算均值、方差去做批归一化，training=True时，通过当前batch的均值、方差去做批归一化。推理时 training=False效果好
return x
有了结构块，就可以搭建精简的网络结构如下，网络共有10层：
2、完整代码
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, \
GlobalAveragePooling2D
from tensorflow.keras import Model
np.set_printoptions(threshold=np.inf)
cifar10 = tf.keras.datasets.cifar10
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
# 定义Inception结构块中的一个CBA，新的类ConvBNRelu，用于后面多次调用
class ConvBNRelu(Model):
def __init__(self, ch, kernelsz=3, strides=1, padding='same'):
super(ConvBNRelu, self).__init__()
self.model = tf.keras.models.Sequential([
Conv2D(ch, kernelsz, strides=strides, padding=padding),
BatchNormalization(),
Activation('relu')
])
def call(self, x):
x = self.model(x, training=False) #在training=False时，BN通过整个训练集计算均值、方差去做批归一化，training=True时，通过当前batch的均值、方差去做批归一化。推理时 training=False效果好
return x
# Inception结构块
class InceptionBlk(Model):
def __init__(self, ch, strides=1):
super(InceptionBlk, self).__init__()
self.ch = ch
self.strides = strides
# 第一个分支
self.c1 = ConvBNRelu(ch, kernelsz=1, strides=strides)
# 第二个分支
self.c2_1 = ConvBNRelu(ch, kernelsz=1, strides=strides)
self.c2_2 = ConvBNRelu(ch, kernelsz=3, strides=1)
# 第三个分支
self.c3_1 = ConvBNRelu(ch, kernelsz=1, strides=strides)
self.c3_2 = ConvBNRelu(ch, kernelsz=5, strides=1)
# 第四个分支
self.p4_1 = MaxPool2D(3, strides=1, padding='same')
self.c4_2 = ConvBNRelu(ch, kernelsz=1, strides=strides)
def call(self, x):
x1 = self.c1(x)
x2_1 = self.c2_1(x)
x2_2 = self.c2_2(x2_1)
x3_1 = self.c3_1(x)
x3_2 = self.c3_2(x3_1)
x4_1 = self.p4_1(x)
x4_2 = self.c4_2(x4_1)
# concat along axis=channel
# 四个分支的输出，使用tf.concat使他们堆叠在一起，axis=3指定堆叠的维度是沿深度方向
x = tf.concat([x1, x2_2, x3_2, x4_2], axis=3)
return x
# 定义Inception10网络时，默认init_ch=16，也就是默认输出深度是16
class Inception10(Model):
def __init__(self, num_blocks, num_classes, init_ch=16, **kwargs):
super(Inception10, self).__init__(**kwargs)
self.in_channels = init_ch
self.out_channels = init_ch
self.num_blocks = num_blocks
self.init_ch = init_ch
self.c1 = ConvBNRelu(init_ch)
self.blocks = tf.keras.models.Sequential()
for block_id in range(num_blocks):
for layer_id in range(2):
if layer_id == 0:
# 每个block中的第一个结构块
block = InceptionBlk(self.out_channels, strides=2)
else:
# 每个block中的第二个结构块
block = InceptionBlk(self.out_channels, strides=1)
self.blocks.add(block)
# enlarger out_channels per block
# 输出特征图深度加深，尽可能保证信息承载能力
self.out_channels *= 2
self.p1 = GlobalAveragePooling2D()
self.f1 = Dense(num_classes, activation='softmax')
def call(self, x):
x = self.c1(x)
x = self.blocks(x)
x = self.p1(x)
y = self.f1(x)
return y
model = Inception10(num_blocks=2, num_classes=10)
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['sparse_categorical_accuracy'])
checkpoint_save_path = "./checkpoint/Inception10.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)
history = model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1,
callbacks=[cp_callback])
model.summary()
# 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()
############################################### show ###############################################
# 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.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()
六、ResNet
1、网络介绍
实验证明，单纯堆叠神经网络层数，会使神经网络模型退化，以至于后边的特征丢失了前边特征的原本模样。
ResNet提出了层间残差跳连，引入了前方信息，缓解梯度消失，使神经网络层数增加成为可能。
ResNet块：
ResNet块的连接有两种情况：
一种在堆叠卷积前后维度不同，一种在堆叠卷积前后维度相同。
1×1卷积操作可通过步长改变特征图尺寸，通过卷积核个数改变特征图深度。
ResnetBlock类
将ResNet块的两种结构封装到一个块中，写出ResnetBlock类。
class ResnetBlock(Model):
def __init__(self, filters, strides=1, residual_path=False):
super(ResnetBlock, self).__init__()
self.filters = filters
self.strides = strides
self.residual_path = residual_path
self.c1 = Conv2D(filters, (3, 3), strides=strides, padding='same', use_bias=False)
self.b1 = BatchNormalization()
self.a1 = Activation('relu')
self.c2 = Conv2D(filters, (3, 3), strides=1, padding='same', use_bias=False)
self.b2 = BatchNormalization()
# residual_path为True时，对输入进行下采样，即用1x1的卷积核做卷积操作，保证x能和F(x)维度相同，顺利相加
if residual_path:
self.down_c1 = Conv2D(filters, (1, 1), strides=strides, padding='same', use_bias=False)
self.down_b1 = BatchNormalization()
self.a2 = Activation('relu')
def call(self, inputs):
residual = inputs # residual等于输入值本身，即residual=x
# 将输入通过卷积、BN层、激活层，计算F(x)
x = self.c1(inputs)
x = self.b1(x)
x = self.a1(x)
x = self.c2(x)
y = self.b2(x)
if self.residual_path:
residual = self.down_c1(inputs)
residual = self.down_b1(residual)
out = self.a2(y + residual) # 最后输出的是两部分的和，即F(x)+x或F(x)+Wx,再过激活函数
return out
完整网络结构
2、完整代码
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
np.set_printoptions(threshold=np.inf)
cifar10 = tf.keras.datasets.cifar10
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
# Resne块代码
class ResnetBlock(Model):
def __init__(self, filters, strides=1, residual_path=False):
super(ResnetBlock, self).__init__()
self.filters = filters
self.strides = strides
self.residual_path = residual_path
self.c1 = Conv2D(filters, (3, 3), strides=strides, padding='same', use_bias=False)
self.b1 = BatchNormalization()
self.a1 = Activation('relu')
self.c2 = Conv2D(filters, (3, 3), strides=1, padding='same', use_bias=False)
self.b2 = BatchNormalization()
# residual_path为True时，对输入进行下采样，即用1x1的卷积核做卷积操作，保证x能和F(x)维度相同，顺利相加
if residual_path:
self.down_c1 = Conv2D(filters, (1, 1), strides=strides, padding='same', use_bias=False)
self.down_b1 = BatchNormalization()
self.a2 = Activation('relu')
def call(self, inputs):
residual = inputs # residual等于输入值本身，即residual=x
# 将输入通过卷积、BN层、激活层，计算F(x)
x = self.c1(inputs)
x = self.b1(x)
x = self.a1(x)
x = self.c2(x)
y = self.b2(x)
if self.residual_path:
residual = self.down_c1(inputs)
residual = self.down_b1(residual)
out = self.a2(y + residual) # 最后输出的是两部分的和，即F(x)+x或F(x)+Wx,再过激活函数
return out
# ResNet18的网络结构，调用ResnetBlock
class ResNet18(Model):
def __init__(self, block_list, initial_filters=64): # block_list表示每个block有几个卷积层
super(ResNet18, self).__init__()
self.num_blocks = len(block_list) # 共有几个block
self.block_list = block_list
self.out_filters = initial_filters
self.c1 = Conv2D(self.out_filters, (3, 3), strides=1, padding='same', use_bias=False)
self.b1 = BatchNormalization()
self.a1 = Activation('relu')
self.blocks = tf.keras.models.Sequential()
# 构建ResNet网络结构
for block_id in range(len(block_list)): # 第几个resnet block
for layer_id in range(block_list[block_id]): # 第几个卷积层
if block_id != 0 and layer_id == 0: # 对除第一个block以外的每个block的输入进行下采样
block = ResnetBlock(self.out_filters, strides=2, residual_path=True)
else:
block = ResnetBlock(self.out_filters, residual_path=False)
self.blocks.add(block) # 将构建好的block加入resnet
self.out_filters *= 2 # 下一个block的卷积核数是上一个block的2倍
self.p1 = tf.keras.layers.GlobalAveragePooling2D()
self.f1 = tf.keras.layers.Dense(10, activation='softmax', kernel_regularizer=tf.keras.regularizers.l2())
def call(self, inputs):
x = self.c1(inputs)
x = self.b1(x)
x = self.a1(x)
x = self.blocks(x)
x = self.p1(x)
y = self.f1(x)
return y
model = ResNet18([2, 2, 2, 2])
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['sparse_categorical_accuracy'])
checkpoint_save_path = "./checkpoint/ResNet18.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)
history = model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1,
callbacks=[cp_callback])
model.summary()
# 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()
############################################### show ###############################################
# 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.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()
七、总结
