MNIST数据集

MNIST数据集
tensorflow实现mnist数据集的前向传播、后向传播、测试的代码（4层全连接层）。
mnist数据集有60000张训练数据集和10000张测试数据集，每张图片的大小为28*28。
1.使用五步加载数据集对数据集预处理
2.构造参数（w，b）
3.利用激活函数前向传播获得输出值
4.计算loss（真实值与输出值计算）
5.利用梯度反向传播更新参数
6.测试

import  tensorflow as tf
from    tensorflow import keras
from    tensorflow.keras import layers
from    tensorflow.keras import datasets
import  os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

# x: [60k, 28, 28], x_test：[10k, 28, 28]
# y: [60k], y_test:[10k]
(x, y), (x_test, y_test)= datasets.mnist.load_data()

#将数据转换成tensor
# x: [0~255] => [0~1.] 归一化
#y:表示0-9十个数字类型
x = tf.convert_to_tensor(x, dtype=tf.float32) / 255.
y = tf.convert_to_tensor(y, dtype=tf.int32)
x_test = tf.convert_to_tensor(x_test, dtype=tf.float32) / 255.
y_test = tf.convert_to_tensor(y_test, dtype=tf.int32)
#查看x，y的数据类型，最大值，最小值
print(x.shape, y.shape, x.dtype, y.dtype)
print(tf.reduce_min(x), tf.reduce_max(x))
print(tf.reduce_min(y), tf.reduce_max(y))

#创建数据集batch（128）一次能取128个数据（图片）
train_db = tf.data.Dataset.from_tensor_slices((x,y)).batch(128)
test_db = tf.data.Dataset.from_tensor_slices((x_test,y_test)).batch(128)
#迭代器不停迭代，直到将加载的数据集完全取出，每一次取x:[128, 28, 28], y:[128]
train_iter = iter(train_db)
sample = next(train_iter)
print('batch:', sample[0].shape, sample[1].shape)

#构造参数
# [b, 784] => [b, 256] => [b, 128] => [b, 64] => [b, 10]
# [dim_in, dim_out], [dim_out]
# 隐藏层1张量
#裁剪的正态分布随机数
w1 = tf.Variable(tf.random.truncated_normal([784, 256], stddev=0.1))
b1 = tf.Variable(tf.zeros([256]))
# 隐藏层2张量
w2 = tf.Variable(tf.random.truncated_normal([256, 128], stddev=0.1))
b2 = tf.Variable(tf.zeros([128]))
# 隐藏层3张量
w3 = tf.Variable(tf.random.truncated_normal([128, 64], stddev=0.1))
b3 = tf.Variable(tf.zeros([64]))
# 输出层张量
w4 = tf.Variable(tf.random.truncated_normal([64, 10], stddev=0.1))
b4 = tf.Variable(tf.zeros([10]))

lr = 1e-3

for epoch in range(10): # iterate db for 10
    for step, (x, y) in enumerate(train_db): # for every batch
        # x:[128, 28, 28]
        # y: [128]

        # [b, 28, 28] => [b, 28*28]  维度变换
        x = tf.reshape(x, [-1, 28*28]) 
        
        #前向传播
        with tf.GradientTape() as tape: # 默认跟踪tf.Variable类型的数据，需要将w，b从tensor转成variable
            # x: [b, 28*28]
            #  隐藏层1前向计算，[b, 28*28] => [b, 256]
            h1 = x@w1 + tf.broadcast_to(b1, [x.shape[0], 256])
            h1 = tf.nn.relu(h1)
            # 隐藏层2前向计算，[b, 256] => [b, 128]
            h2 = h1@w2 + b2
            h2 = tf.nn.relu(h2)
            # 隐藏层3前向计算，[b, 128] => [b, 64] 
            h3 = h2@w3 + b3
            h3 = tf.nn.relu(h3)
            # 输出层前向计算，[b, 64] => [b, 10] 
            h4 = h3@w4 + b4
            out = h4

            # 计算误差loss
            # out: [b, 10]
            # y: [b] => [b, 10]
            y_onehot = tf.one_hot(y, depth=10)

            # 均方差：mse = mean(sum(y-out)^2)
            # [b, 10]
            loss = tf.square(y_onehot - out)
            # mean: scalar（标量）
            loss = tf.reduce_mean(loss)
        
        #后向传播，修改参数
        # compute gradients（计算梯度）
        grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3, w4, b4])
        # print(grads)
        # w1 = w1 - lr * w1_grad
        w1.assign_sub(lr * grads[0])  #原地更新参数
        b1.assign_sub(lr * grads[1])
        w2.assign_sub(lr * grads[2])
        b2.assign_sub(lr * grads[3])
        w3.assign_sub(lr * grads[4])
        b3.assign_sub(lr * grads[5])
        w4.assign_sub(lr * grads[6])
        b4.assign_sub(lr * grads[7])


        if step % 100 == 0: #每100次输出loss的值
            print(epoch, step, 'loss:', float(loss))


    #test
    #使用当前阶段的参数进行测试[w1, b1, w2 ,b2, w3, b3, w4, b4]
    total_correct, total_num = 0, 0
    for step,(x,y) in enumerate(test_db):

        #[b, 28, 28] ==>[b, 28*28]
        x = tf.reshape(x,[-1,28*28])

        #[b, 784] ==> [b,256] ==> [b,128] ==> [b,10]
        h1 = tf.nn.relu(x@w1 + b1)
        h2 = tf.nn.relu(h1@w2 + b2)
        h3 = tf.nn.relu(h2@w3 + b3)
        out = h3@w4 + b4

        #out:[b, 10] - R
        #prob:[b, 10] - [0,1]计算输出值的概率（softmax）
        prob = tf.nn.softmax(out, axis=1)

        #[b, 10] ==> [b]  获取概率最大值的索引位置
        pred = tf.argmax(prob, axis=1)
        pred = tf.cast(pred, dtype=tf.int32)  #将pred；int64转为int32
        #print(pred.dtype,y.dtype)

        #y:[b]
        #[b],int32   equal比较预测值与真实值，相同返回True，不同返回False，再转换成int(0,1)
        correct = tf.cast(tf.equal(pred, y), dtype = tf.int32)
        correct = tf.reduce_sum(correct)  #预测正确值为1，统计预测正确的个数

        total_correct += int(correct)  #总的正确个数
        total_num += x.shape[0]  #总的测试个数

    acc = total_correct/total_num #预测得分
    print('test acc:',acc)