AlexNet的网络架构
import tensorflow as tf
net=tf.keras.models.Sequential([
tf.keras.layers.Conv2D(filters=96,kernel_size=11,strides=4,activation='relu'),
tf.keras.layers.MaxPool2D(pool_size=3,strides=2),
tf.keras.layers.Conv2D(filters=256,kernel_size=5,padding='same',activation='relu'),
tf.keras.layers.MaxPool2D(pool_size=3,strides=2),
tf.keras.layers.Conv2D(filters=384,kernel_size=3,padding='same',activation='relu'),
tf.keras.layers.Conv2D(filters=384,kernel_size=3,padding='same',activation='relu'),
tf.keras.layers.Conv2D(filters=256,kernel_size=3,padding='same',activation='relu'),
tf.keras.layers.MaxPool2D(pool_size=3,strides=2),
tf.keras.layers.Flatten(), #展开,也就是变成一维向量
tf.keras.layers.Dense(4096,activation='relu'),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.Dense(4096,activation='relu'),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.Dense(10,activation='softmax')
])
x=tf.random.uniform((1,227,227,1))
y=net(x)
net.summary()
手写数字识别
数据读取
from tensorflow.keras.datasets import mnist
import tensorflow as tf
import numpy as np
(train_images,train_labels),(test_images,test_labels)=mnist.load_data()
#维度调整
train_images=np.reshape(train_images,(train_images.shape[0],train_images.shape[1],train_images.shape[2],1))
test_images=np.reshape(test_images,(test_images.shape[0],test_images.shape[1],test_images.shape[2],1))
#对训练数据进行抽样
def get_train(size):
#随机生成index
index=np.random.randint(0,train_images.shape[0],size)
#选择图像并进行resize
resized_image=tf.image.resize_with_pad(train_images[index],227,227)
return resized_image.numpy(),train_labels[index]
#对测试数据进行抽样
def get_test(size):
#随机生成index
index=np.random.randint(0,test_images.shape[0],size)
#选择图像并进行resize
resized_image=tf.image.resize_with_pad(test_images[index],227,227)
return resized_image.numpy(),test_labels[index]
train_images,train_labels=get_train(256)
test_images,test_labels=get_test(128)
模型编译
#模型编译
net.compile(optimizer=tf.keras.optimizers.SGD(learning_rate=0.01),
loss=tf.keras.losses.sparse_categorical_crossentropy,
metrics=['accuracy'])
模型训练
net.fit(train_images,train_labels,batch_size=128,epochs=3,validation_split=0.1)
模型评估
net.evaluate(test_images,test_labels)