AlexNet实现cifar10数据集分类

import tensorflow as tf
import os
from matplotlib import pyplot as plt
import tensorflow.keras.datasets
from tensorflow.keras import  Model
import numpy as np
from tensorflow.keras.layers import Dense,Flatten,BatchNormalization,Dropout,Conv2D,Activation,MaxPool2D
cifar10=tf.keras.datasets.cifar10
(x_train,y_train),(x_test,y_test)=cifar10.load_data()
x_train=x_train/255.
x_test=x_test/255.


class AlexNet(Model):
    def __init__(self):
        super(AlexNet, self).__init__()
        self.c1=Conv2D(filters=96,kernel_size=(3,3),strides=1,padding='valid')
        self.b1=BatchNormalization()
        self.a1=Activation('relu')
        self.p1=MaxPool2D(pool_size=(3,3),strides=2)

        self.c2 = Conv2D(filters=384, kernel_size=(3, 3), strides=1, padding='same')
        #self.b2 = BatchNormalization()
        self.a2 = Activation('relu')
        #self.p2 = MaxPool2D(pool_size=(3, 3), strides=2)

        self.c3 = Conv2D(filters=256, kernel_size=(3, 3), strides=1, padding='same')
        # self.b2 = BatchNormalization()
        self.a3 = 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.a2(x)

        x = self.c3(x)
        x = self.a3(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=AlexNet()

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

check_save_path='./checkpoint/AlexNet.ckpt'
if os.path.exists(check_save_path+'.index'):
    print('-------------lodel the model------------')
    model.load_weights(check_save_path)

cp_callback=tf.keras.callbacks.ModelCheckpoint(filepath=check_save_path,save_best_only=True,
                                                save_weights_only=True)

history=model.fit(x_train,y_train,batch_size=128,epochs=5,validation_data=(x_test,y_test),
                  validation_freq=1,callbacks=[cp_callback])

model.summary()

file=open('./AlexNet_wights.txt','w')
for v in model.trainable_variables:
    file.write(str(v.name) + '\n')
    file.write(str(v.shape) + '\n')
    file.write(str(v.np()) + '\n')
file.close()


############可视化图像###############
acc=history.history['sparse_categorical_accuracy']
val_acc=history.history['sparse_categorical_val_accuracy']
loss=history.history['loss']
val_loss=history.history['val_loss']

plt.subplot(1,2,1)
plt.plot(acc)
plt.plot(val_acc)
plt.legend()

plt.subplot(1,2,2)
plt.plot(loss)
plt.plot(val_loss)
plt.legend()

plt.show()

此代码运行较慢，单次遍历需要近15分钟，由此可见两层全连接层2048个神经元远远拖慢运行速度