Tensorflow实现手写数字识别

复制代码
import tensorflow as tf
import numpy as np
class MNISTLoader(object):
    """数据加载处理类
    """
    def __init__(self):
        """
        """
        # 1、获取数据    
        (self.train_data, self.train_label), (self.test_data, self.test_label) = tf.keras.datasets.mnist.load_data()
        # 2、处理数据，归一化，维度以及类型
        # MNIST中的图像默认为uint8（0-255的数字）。以下代码将其归一化到0-1之间的浮点数，并在最后增加一维作为颜色通道
        # 默认下载是(60000, 28, 28)，扩展到四维方便计算理解[60000, 28, 28, 1]
        self.train_data = np.expand_dims(self.train_data.astype(np.float32) / 255.0, axis=-1)
        # [10000, 28, 28, 1]
        self.test_data = np.expand_dims(self.test_data.astype(np.float32) / 255.0, axis=-1)
        self.train_label = self.train_label.astype(np.int32)    # [60000]
        self.test_label = self.test_label.astype(np.int32)      # [10000]
        # 获取数据的大小
        self.num_train_data, self.num_test_data = self.train_data.shape[0], self.test_data.shape[0]

    def get_batch(self, batch_size):
        """
        随机获取获取批次数据
        :param batch_size: 批次大小
        :return:
        """
        # 从数据集中随机取出batch_size个元素并返回
        index = np.random.randint(0, np.shape(self.train_data)[0], batch_size)
        return self.train_data[index, :], self.train_label[index]




class MLP(tf.keras.Model):
    """自定义MLP类
    """
    def __init__(self):
        super().__init__()
        # 定义两层神经网络，第一层100个神经元，激活函数relu，第二层10个神经元输出给softmax
        self.flatten = tf.keras.layers.Flatten()
        self.dense1 = tf.keras.layers.Dense(units=100, activation=tf.nn.relu)
        self.dense2 = tf.keras.layers.Dense(units=10)

    def call(self, inputs):
        # [batch_size, 28, 28, 1]
        x = self.flatten(inputs)
        # [batch_size, 784]
        x = self.dense1(x)
        # [batch_size, 100]
        x = self.dense2(x)
        # [batch_size, 10]
        output = tf.nn.softmax(x)
        return output

num_epochs = 5
batch_size = 50
learning_rate = 0.001

# 实例化模型和数据读取类，并实例化一个优化器，这里使用 Adam 优化器
model = MLP()
data_loader = MNISTLoader()
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
# 计算出大概需要迭代批次大小
num_batches = int(data_loader.num_train_data // batch_size * num_epochs)
        # 进行批次数据获取
for batch_index in range(num_batches):
    X, y = data_loader.get_batch(batch_size)
    with tf.GradientTape() as tape:
        y_pred = model(X)
        # 使用tf.keras.losses计算损失
        loss = tf.keras.losses.sparse_categorical_crossentropy(y_true=y, y_pred=y_pred)
        # 求出平均损失
        loss = tf.reduce_mean(loss)
        print("batch %d: loss %f" % (batch_index, loss.numpy()))
    grads = tape.gradient(loss, model.variables)
    optimizer.apply_gradients(grads_and_vars=zip(grads, model.variables))

y_pred = model.predict(data_loader.test_data)
# 定义评估函数
sparse_categorical_accuracy = tf.keras.metrics.SparseCategoricalAccuracy()
# 定义测试数据集一共批次的大小
sparse_categorical_accuracy.update_state(y_true=data_loader.test_label, y_pred=y_pred)
print("测试准确率: %f" % sparse_categorical_accuracy.result())