Keras：MNIST数字图像识别示例

# !/user/bin/env python
# -*- coding:utf-8 -*-
from keras.datasets import mnist
from keras.utils import to_categorical
from keras import layers
from keras import models

# import keras.backend.tensorflow_backend as KTF
# import tensorflow as tf
# import os
# os.environ["CUDA_VISIBLE_DEVICES"] = "0"
# config = tf.ConfigProto()
# config.gpu_options.allow_growth=True #不全部占满显存, 按需分配
# sess = tf.Session(config=config)
# KTF.set_session(sess)

# 模型结构
# 卷积层
model = models.Sequential()
model.add(layers.Conv2D(32, (2, 2), activation='relu', input_shape=(28, 28, 1)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.summary()

# 全连接层
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))
model.summary()

# 加载数据集
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
train_images = train_images.reshape((60000, 28, 28, 1))
train_images = train_images.astype('float32') / 255


test_images = test_images.reshape((60000, 28, 28, 1))
test_images = test_images.astype('float32') / 255

train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)
# 编译
model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
# 训练
model.fit(train_images, train_labels, epochs=5, batch_size=6)

# 测试
test_loss, test_acc = model.evaluate(test_images, test_labels)
print(test_acc)