Tensorflow2教程-基础CNN网络

Tensorflow 2.0 教程持续更新https://blog.csdn.net/qq_31456593/article/details/88606284

完整tensorflow2.0教程代码请看tensorflow2.0:中文教程tensorflow2_tutorials_chinese(欢迎star)

入门教程:
TensorFlow 2.0 教程- Keras 快速入门
TensorFlow 2.0 教程-keras 函数api
TensorFlow 2.0 教程-使用keras训练模型
TensorFlow 2.0 教程-用keras构建自己的网络层
TensorFlow 2.0 教程-keras模型保存和序列化

tensorflow2-基础CNN网络

1.构造数据


(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()

print(x_train.shape, ' ', y_train.shape)
print(x_test.shape, ' ', y_test.shape)

(60000, 28, 28)   (60000,)
(10000, 28, 28)   (10000,)
import matplotlib.pyplot as plt
plt.imshow(x_train[0])
plt.show()

png


x_train = x_train.reshape((-1,28,28,1))
x_test = x_test.reshape((-1,28,28,1))

2.构造网络

model = keras.Sequential()

卷积层

model.add(layers.Conv2D(input_shape=(x_train.shape[1], x_train.shape[2], x_train.shape[3]),
                        filters=32, kernel_size=(3,3), strides=(1,1), padding='valid',
                       activation='relu'))

池化层

model.add(layers.MaxPool2D(pool_size=(2,2)))

全连接层

model.add(layers.Flatten())
model.add(layers.Dense(32, activation='relu'))
# 分类层
model.add(layers.Dense(10, activation='softmax'))

3.模型配置

model.compile(optimizer=keras.optimizers.Adam(),
             # loss=keras.losses.CategoricalCrossentropy(),  # 需要使用to_categorical
             loss=keras.losses.SparseCategoricalCrossentropy(),
              metrics=['accuracy'])
model.summary()
Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_2 (Conv2D)            (None, 26, 26, 32)        320       
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 13, 13, 32)        0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 5408)              0         
_________________________________________________________________
dense_2 (Dense)              (None, 32)                173088    
_________________________________________________________________
dense_3 (Dense)              (None, 10)                330       
=================================================================
Total params: 173,738
Trainable params: 173,738
Non-trainable params: 0
_________________________________________________________________

4.模型训练

history = model.fit(x_train, y_train, batch_size=64, epochs=5, validation_split=0.1)
Train on 54000 samples, validate on 6000 samples
Epoch 1/5
54000/54000 [==============================] - 11s 197us/sample - loss: 0.0589 - accuracy: 0.9825 - val_loss: 0.0963 - val_accuracy: 0.9785
Epoch 2/5
54000/54000 [==============================] - 11s 195us/sample - loss: 0.0500 - accuracy: 0.9849 - val_loss: 0.0957 - val_accuracy: 0.9777
Epoch 3/5
54000/54000 [==============================] - 11s 197us/sample - loss: 0.0429 - accuracy: 0.9867 - val_loss: 0.0881 - val_accuracy: 0.9798
Epoch 4/5
54000/54000 [==============================] - 11s 199us/sample - loss: 0.0381 - accuracy: 0.9877 - val_loss: 0.0811 - val_accuracy: 0.9817
Epoch 5/5
54000/54000 [==============================] - 11s 200us/sample - loss: 0.0340 - accuracy: 0.9890 - val_loss: 0.0910 - val_accuracy: 0.9795
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.legend(['training', 'valivation'], loc='upper left')
plt.show()

png

res = model.evaluate(x_test, y_test)

10000/10000 [==============================] - 1s 73us/sample - loss: 0.1255 - accuracy: 0.9733

已标记关键词 清除标记
©️2020 CSDN 皮肤主题: 撸撸猫 设计师:设计师小姐姐 返回首页