#导入数据
import tensorflow as tf
from tensorflow.keras import datasets,layers,models
import matplotlib.pyplot as plt

(train_images,train_labels),\
(test_images,test_labels) = datasets.cifar10.load_data()

#归一化
#将像素的值标准化至0至1的区间内
train_images,test_images = train_images/255.0,test_images/255.0
train_images.shape,test_images.shape,train_labels.shape,test_labels.shape

((50000, 32, 32, 3), (10000, 32, 32, 3), (50000, 1), (10000, 1))

#可视化
class_names = ['airplane',
               'automobile',
               'bird',
               'cat',
               'deer',
               'dog',
               'frog',
               'horse',
               'ship',
               'truck']

plt.figure(figsize=(20,10))
for i in range(20):
    plt.subplot(5,10,i+1)
    plt.xticks([])
    plt.yticks([])
    plt.grid(False)
    plt.imshow(train_images[i],cmap=plt.cm.binary)
    plt.xlabel(class_names[train_labels[i][0]])
plt.show()

#构建CNN网络
model = models.Sequential([
    layers.Conv2D(32,(3,3),activation='relu',input_shape=(32,32,3)),#卷积层1，卷积核3*3
    layers.MaxPool2D((2,2)),#池化层1，2*2采样
    layers.Conv2D(64,(3,3),activation='relu'),#卷积层2，卷积核3*3
    layers.MaxPooling2D((2,2)),#池化层2，2*2采样
    layers.Conv2D(64,(3,3),activation='relu'),#卷积层3，卷积核3*3
    
    layers.Flatten(),#Flattern层，连接卷积层与全连接层
    layers.Dense(64,activation='relu'),#全连接层，特征进一步提取
    layers.Dense(10)#输出层，输出预期结果
])
model.summary()#打印网络结构

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_3 (Conv2D)            (None, 30, 30, 32)        896       
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 15, 15, 32)        0         
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 13, 13, 64)        18496     
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 6, 6, 64)          0         
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 4, 4, 64)          36928     
_________________________________________________________________
flatten_1 (Flatten)          (None, 1024)              0         
_________________________________________________________________
dense_2 (Dense)              (None, 64)                65600     
_________________________________________________________________
dense_3 (Dense)              (None, 10)                650       
=================================================================
Total params: 122,570
Trainable params: 122,570
Non-trainable params: 0
_________________________________________________________________

#编译
model.compile(optimizer='adam',
             loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
             metrics=['accuracy'])

#训练模型
history = model.fit(train_images,
                    train_labels,
                   epochs=10,
                   validation_data=[test_images,test_labels])

Train on 50000 samples, validate on 10000 samples
Epoch 1/10
50000/50000 [==============================] - 166s 3ms/sample - loss: 1.5062 - accuracy: 0.4532 - val_loss: 1.2831 - val_accuracy: 0.5346
Epoch 2/10
50000/50000 [==============================] - 167s 3ms/sample - loss: 1.1461 - accuracy: 0.5947 - val_loss: 1.0774 - val_accuracy: 0.6263
Epoch 3/10
50000/50000 [==============================] - 163s 3ms/sample - loss: 0.9935 - accuracy: 0.6513 - val_loss: 1.0326 - val_accuracy: 0.6389
Epoch 4/10
50000/50000 [==============================] - 163s 3ms/sample - loss: 0.8971 - accuracy: 0.6864 - val_loss: 0.9665 - val_accuracy: 0.6581
Epoch 5/10
50000/50000 [==============================] - 164s 3ms/sample - loss: 0.8210 - accuracy: 0.7110 - val_loss: 0.9175 - val_accuracy: 0.6827
Epoch 6/10
50000/50000 [==============================] - 162s 3ms/sample - loss: 0.7626 - accuracy: 0.7336 - val_loss: 0.9316 - val_accuracy: 0.6854
Epoch 7/10
50000/50000 [==============================] - 162s 3ms/sample - loss: 0.7129 - accuracy: 0.7515 - val_loss: 0.9221 - val_accuracy: 0.6894
Epoch 8/10
50000/50000 [==============================] - 167s 3ms/sample - loss: 0.6663 - accuracy: 0.7655 - val_loss: 0.8944 - val_accuracy: 0.7061
Epoch 9/10
50000/50000 [==============================] - 162s 3ms/sample - loss: 0.6244 - accuracy: 0.7807 - val_loss: 0.8967 - val_accuracy: 0.7041
Epoch 10/10
50000/50000 [==============================] - 167s 3ms/sample - loss: 0.5905 - accuracy: 0.7918 - val_loss: 0.8741 - val_accuracy: 0.7193

预测(通过模型进行得到的是每个类别的概率，数字越大该图片为类别的可能性越大)

plt.imshow(test_images[1])

<matplotlib.image.AxesImage at 0x7fc849626410>

import numpy as np
pre = model.predict(test_images)
print(class_names[np.argmax(pre[1])])

ship

#模型评估
import matplotlib.pyplot as plt

plt.plot(history.history['accuracy'],label='accuracy')
plt.plot(history.history['val_accuracy'],label = 'val_accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.show()

test_loss,test_acc = model.evaluate(test_images,
                                    test_labels,
                                    verbose=2)

10000/1 - 11s - loss: 0.8913 - accuracy: 0.7193

print(test_acc)

0.7193

• loss：训练集损失值

• accuracy:训练集准确率

• val_loss:测试集损失值

• val_accruacy:测试集准确率