代码

import os
import tensorflow as tf
os.environ['CUDA_VISIBLE_DEVICES'] = '2,3'
from tensorflow.keras import datasets, layers, models


class CNN(object):
    def __init__(self):
        model = models.Sequential()
        # 第1层卷积，卷积核大小为3*3，32个，28*28为待训练图片的大小
        model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
        model.add(layers.MaxPooling2D((2, 2)))
        # 第2层卷积，卷积核大小为3*3，64个
        model.add(layers.Conv2D(64, (3, 3), activation='relu'))
        model.add(layers.MaxPooling2D((2, 2)))
        # 第3层卷积，卷积核大小为3*3，64个
        model.add(layers.Conv2D(64, (3, 3), activation='relu'))

        model.add(layers.Flatten())
        model.add(layers.Dense(64, activation='relu'))
        model.add(layers.Dense(10, activation='softmax'))

        model.summary()

        self.model = model


class DataSource(object):
    def __init__(self):
        # mnist数据集存储的位置，如何不存在将自动下载
        # data_path = os.path.abspath(os.path.dirname(__file__)) + 'D:/python/Tensorflow/data_set_tf2/mnist.npz'
        # data_path = os.path.abspath('D:/python/Tensorflow/data_set_tf2/mnist.npz')
        # data_path = 'D:/python/Tensorflow/data_set_tf2/mnist.npz'
        # (train_images, train_labels), (test_images, test_labels) = datasets.mnist.load_data(path=data_path)
        mnist = tf.keras.datasets.mnist
        (x_train, y_train), (x_test, y_test) = mnist.load_data()
        x_train4D = x_train.reshape(x_train.shape[0], 28, 28, 1).astype('float32')
        x_test4D = x_test.reshape(x_test.shape[0], 28, 28, 1).astype('float32')
        # 像素标准化
        x_train, x_test = x_train4D / 255.0, x_test4D / 255.0
        # # 6万张训练图片，1万张测试图片
        # train_images = train_images.reshape((60000, 28, 28, 1))
        # test_images = test_images.reshape((10000, 28, 28, 1))
        # # 像素值映射到 0 - 1 之间
        # train_images, test_images = train_images / 255.0, test_images / 255.0

        self.train_images, self.train_labels = x_train, y_train
        self.test_images, self.test_labels = x_test, y_test

class Train:
    def __init__(self):
        self.cnn = CNN()
        self.data = DataSource()

    def train(self):
        check_path = './ckpt/cp-{epoch:04d}.ckpt'
        # if os.path.exits(check_path + '.index'):
        #     print('--------------------load the model--------------------')
        #     models.load_weights(check_path)
        cp_callback = tf.keras.callbacks.ModelCheckpoint(
            filepath=check_path,
            save_weights_only=True,
            save_best_only=True,
            verbose = 1, period = 5
        )
        # period 每隔5epoch保存一次
        # save_model_cb = tf.keras.callbacks.ModelCheckpoint(check_path, save_weights_only=True, verbose=1, period=5)

        self.cnn.model.compile(optimizer='adam',
                               loss='sparse_categorical_crossentropy',
                               metrics=['accuracy'])
        self.cnn.model.fit(self.data.train_images, self.data.train_labels, epochs=5, callbacks=[cp_callback])

        test_loss, test_acc = self.cnn.model.evaluate(self.data.test_images, self.data.test_labels)
        print("准确率: %.4f，共测试了%d张图片 " % (test_acc, len(self.data.test_labels)))


if __name__ == "__main__":
    app = Train()
    app.train()