InceptionNet网络搭建
网络结构及分析:
如上图,InceptionNet是由一个卷积层+四个Inception结构块+所有通道进行平均池化的池化层+Dense层组成
四个Inception结构块的上面两个组成一个block,下面两个组成一个block
block中的第一个Inception结构块卷积步长是2
第二个Inception结构块卷积步长是1
Inception结构块的结构
输入经过四路进入卷积连接器(Filter concatenation)
上图中的Inception结构块的每一个卷积层都是执行的CBA操作,如
所以可将CBA操作封装到一个类ConvBNRelu中:
class ConvBNRelu(Model):
def __init__(self, ch, kernelsz=3, strides=1, padding='same'): # ch是卷积核个数,kernelsz是卷积核尺寸,strides是步长
super(ConvBNRelu, self).__init__()
# 将Conv2D,BatchNormalization,Activation封装到一个model里面
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ConvBNRelu,可以方便的搭建出Inception结构块:
class InceptionBlk(Model):
def __init__(self, ch, strides=1):
super(InceptionBlk, self).__init__()
self.ch = ch
self.strides = strides
# c1是Inception结构块的第一个分支,使用一次ConvBNRelu
self.c1 = ConvBNRelu(ch, kernelsz=1, strides=strides)
# c2_1,c2_2是Inception结构块的第二个分支,使用两次ConvBNRelu
self.c2_1 = ConvBNRelu(ch, kernelsz=1, strides=strides)
self.c2_2 = ConvBNRelu(ch, kernelsz=3, strides=1)
self.c3_1 = ConvBNRelu(ch, kernelsz=1, strides=strides)
self.c3_2 = ConvBNRelu(ch, kernelsz=5, strides=1)
# 第四个分支先池化,再卷积
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)
# x1, x2_2, x3_2, x4_2是四个分支的输出,使用tf.concat函数将这四个沿深度方向堆叠在一起
x = tf.concat([x1, x2_2, x3_2, x4_2], axis=3)
return x
有了Inception结构块,便可以搭建出InceptionNet了:
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
# 第一层是一个只有CBA操作的卷积层,可以直接调用ConvBNRelu
self.c1 = ConvBNRelu(init_ch)
self.blocks = tf.keras.models.Sequential()
# 外层循环是循环两个block
for block_id in range(num_blocks):
# 内层循环是循环一个block里面的两个Incption结构块,第一个结构块的卷积步长是2,第二个结构块的卷积步长是1
for layer_id in range(2):
if layer_id == 0:
block = InceptionBlk(self.out_channels, strides=2)
else:
block = InceptionBlk(self.out_channels, strides=1)
self.blocks.add(block)
# enlarger out_channels per block
# 第一个结构块的卷积步长是2,这使得第一个Inception结构块输出特征图尺寸减半,因此把输出特征图深度加深,尽可能保证特征抽取中信息的承载量一致
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) # 实例化,指定block是2,这个问题是10分类的
将以上三块代码合起来即是InceptionNet的网络结构
如果GPU性能较好,可以把batch_size从32改为128,512,1024等,增加一次性喂入神经网络的数据,以增加运算速度
整体代码:
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
class ConvBNRelu(Model):
def __init__(self, ch, kernelsz=3, strides=1, padding='same'): # ch是卷积核个数,kernelsz是卷积核尺寸,strides是步长
super(ConvBNRelu, self).__init__()
# 将Conv2D,BatchNormalization,Activation封装到一个model里面
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
class InceptionBlk(Model):
def __init__(self, ch, strides=1):
super(InceptionBlk, self).__init__()
self.ch = ch
self.strides = strides
# c1是Inception结构块的第一个分支,使用一次ConvBNRelu
self.c1 = ConvBNRelu(ch, kernelsz=1, strides=strides)
# c2_1,c2_2是Inception结构块的第二个分支,使用两次ConvBNRelu
self.c2_1 = ConvBNRelu(ch, kernelsz=1, strides=strides)
self.c2_2 = ConvBNRelu(ch, kernelsz=3, strides=1)
self.c3_1 = ConvBNRelu(ch, kernelsz=1, strides=strides)
self.c3_2 = ConvBNRelu(ch, kernelsz=5, strides=1)
# 第四个分支先池化,再卷积
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)
# x1, x2_2, x3_2, x4_2是四个分支的输出,使用tf.concat函数将这四个沿深度方向堆叠在一起
x = tf.concat([x1, x2_2, x3_2, x4_2], axis=3)
return x
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
# 第一层是一个只有CBA操作的卷积层,可以直接调用ConvBNRelu
self.c1 = ConvBNRelu(init_ch)
self.blocks = tf.keras.models.Sequential()
# 外层循环是循环两个block
for block_id in range(num_blocks):
# 内层循环是循环一个block里面的两个Incption结构块,第一个结构块的卷积步长是2,第二个结构块的卷积步长是1
for layer_id in range(2):
if layer_id == 0:
block = InceptionBlk(self.out_channels, strides=2)
else:
block = InceptionBlk(self.out_channels, strides=1)
self.blocks.add(block)
# enlarger out_channels per block
# 第一个结构块的卷积步长是2,这使得第一个Inception结构块输出特征图尺寸减半,因此把输出特征图深度加深,尽可能保证特征抽取中信息的承载量一致
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) # 实例化,指定block是2,这个问题是10分类的
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=512, 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()