博客

tensorflow笔记1

搭建一个神经网络，训练cifar10数据集，搭建一个一层卷积（卷积核6*5*5conv，pool（2*2），步长2），2层全连接的网络（dense128，dense10）
cifar10数据集一共6万张彩色图片，5万张32*32像素点的图片核标签用于训练，1万张用于测试。里面由10个分类，飞机、汽车、鸟、猫、狗。。。。分别对应标签0-9
神经网络的一个基本模型
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
 
class Baseline(Model):               #前向传播，生成y
    def __init__(self):
        super(Baseline, self).__init__()
        self.c1 = Conv2D(filters=6, kernel_size=(5, 5), padding='same')  # 卷积层
        self.b1 = BatchNormalization()                           # BN层
        self.a1 = Activation('relu')                                 # 激活层
        self.p1 = MaxPool2D(pool_size=(2, 2), strides=2, padding='same')  # 池化层
        self.d1 = Dropout(0.2)                          # dropout层  20%的比例休眠神经元
        self.flatten = Flatten()
        self.f1 = Dense(128, activation='relu')
        self.d2 = Dropout(0.2)
        self.f2 = 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.d1(x)
        x = self.flatten(x)
        x = self.f1(x)
        x = self.d2(x)
        y = self.f2(x)
        return y
model = Baseline()
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])
checkpoint_save_path = "./checkpoint/Baseline.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()
# 显示训练集和验证集的acc和loss曲线  
acc = history.history['sparse_categorical_accuracy']  #提取model.fit函数在训练中保存的训练集准确率
val_acc = history.history['val_sparse_categorical_accuracy']     #测试机准确率
loss = history.history['loss']                              #训练集损失函数数值
val_loss = history.history['val_loss']                            #测试机损失函数数值
 
plt.subplot(1, 2, 1)        #将图象分为1行2列，这个为画出第一列
plt.plot(acc, label='Training Accuracy')
plt.plot(val_acc, label='Validation Accuracy')        #画出这2个图象
plt.title('Training and Validation Accuracy')
plt.legend()             #画出图例

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()








#################################LeNet 5层######################################

class LeNet5(Model):
    def __init__(self):
        super(LeNet5, self).__init__()
        self.c1 = Conv2D(filters=6, kernel_size=(5, 5),activation='sigmoid')
        self.p1 = MaxPool2D(pool_size=(2, 2), strides=2)
        self.c2 = Conv2D(filters=16, kernel_size=(5, 5),activation='sigmoid')
        self.p2 = MaxPool2D(pool_size=(2, 2), strides=2)
        self.flatten = Flatten()
        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()
###################################AlexNet 8层#############################
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()                       VGG 16/19层
###############################InceptionNet 22层##############################
基本单元：Inception结构快，在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，
设定少于输入特征图深度的1*1卷积核个数，起到降维的作用减少了计算量。结构快由4个分支组成，分别经过1*1卷积核输出到卷积连接器........
卷积连接器把收到的四路特征数据按深度方向拼接，形成结构快的输出。
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')
        ])
 #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。
    def call(self, x):
        x = self.model(x, training=False)    #推理时 training=False效果好
        return x

class InceptionBlk(Model):                #Inception结构快
    def __init__(self, ch, strides=1):
        super(InceptionBlk, self).__init__()
        self.ch = ch
        self.strides = strides
        self.c1 = ConvBNRelu(ch, kernelsz=1, strides=strides)
        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)
        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
        x = tf.concat([x1, x2_2, x3_2, x4_2], axis=3)            #axis=3指定堆叠的方向时沿深度方向
        return x

class Inception10(Model):
    def __init__(self, num_blocks, num_classes, init_ch=16, **kwargs):  #输出深度16
        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:
                    block = InceptionBlk(self.out_channels, strides=2)
                else:
                    block = InceptionBlk(self.out_channels, strides=1)
                self.blocks.add(block)
            # enlarger out_channels per block
            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)