TensorFlow04-实现mnist

"""
1. 放入mnist数据到项目根目录mnist/MINIST_data下
"""
def test03_mnist():
    # 载入数据，将数据进行one_hot向量化
    mnist = input_data.read_data_sets('mnist/MNIST_data', one_hot=True)

    # 每个批次的大小
    batch_size = 100
    # 计算共有多少个批次
    n_batch = mnist.train.num_examples // batch_size

    # 定义两个placeholder
    # None:任意值：每个批次一次一次的传值到placeholder中，实现动态传值，比如传100行数据进去，None就变为100
    # 784列:每个图片的为28 * 28的格式，将图片转换为一维数组的方式，所有有 None行、874列
    x = tf.placeholder(tf.float32, [None, 784])
    y = tf.placeholder(tf.float32, [None, 10])    # 一共有10个数字:0-9

    # 创建神经网络
    W = tf.Variable(tf.zeros([784, 10]))
    b = tf.Variable(tf.zeros([10]))
    prediction = tf.nn.softmax(tf.matmul(x, W) + b)

    # 定义二次代价函数
    loss = tf.reduce_mean(tf.square(y-prediction))
    # 使用梯度下降法
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

    # 初始化变量
    init = tf.global_variables_initializer()

    # 结果存放在一个bool列表中
    # argmax返回一个一维张量中最大的值所在的位置
    correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(prediction, 1))
    # 求准确率
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    with tf.Session() as sess:
        sess.run(init)
        for e in range(200):
            for batch in range(n_batch):
                batch_xs, batch_ys = mnist.train.next_batch(batch_size)
                sess.run(train_step, feed_dict={x: batch_xs, y: batch_ys})

            acc = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels})
            print("Iter" + str(e) + ", Testing Accuracy " + str(acc))




if __name__ == "__main__":
    test03_mnist()