mnist数据集前向传播实现

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import datasets
import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
# x:[60000, 28, 28] y:[60000,]

(x, y), _ = datasets.mnist.load_data()

# x:[0-255]=>[0-1]
x = tf.convert_to_tensor(x, dtype=tf.float32) / 255.
y = tf.convert_to_tensor(y, dtype=tf.int32)
# 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))

train_db = tf.data.Dataset.from_tensor_slices((x, y)).batch(128)
train_iter = iter(train_db)
sample = next(train_iter)
# print('batch:',sample[0].shape,sample[1].shape)

# [b,784] => [b,256] =>[b,128] =>[b,10]
w1 = tf.Variable(tf.random.truncated_normal([784, 256], stddev=0.1))
b1 = tf.Variable(tf.zeros([256]))
w2 = tf.Variable(tf.random.truncated_normal([256, 128], stddev=0.1))
b2 = tf.Variable(tf.zeros([128]))
w3 = tf.Variable(tf.random.truncated_normal([128, 10], stddev=0.1))
b3 = tf.Variable(tf.zeros([10]))
lr = 1e-3
for epoch in range(10):
    for step,(x, y) in enumerate(train_db):
        # x:[128,28,28]
        # y:[128]
        # x:[128,28,28] =>[b,28*28]
        x = tf.reshape(x, [-1, 28 * 28])
        # [b, 784]@[784, 256] + [256] =>[b, 256]
        with tf.GradientTape() as tape:
            h1 = x @ w1 + b1
            h1 = tf.nn.relu(h1)
            h2 = h1 @ w2 + b2
            h2 = tf.nn.relu(h2)
            out = h2 @ w3 + b3

            # compute loss
            y_onehot = tf.one_hot(y, depth=10)
            # mse = mean(y-out)**2
            loss = tf.reduce_mean(tf.square(y_onehot - out))
        # compute gradients
        grads = tape.gradient(loss, [w1, w2, w3, b1, b2, b3])
        # print(grads)
        # w1 = w1 -lr* w1_grad
        w1.assign_sub(lr *grads[0])
        w2.assign_sub(lr *grads[1])
        w3.assign_sub(lr *grads[2])
        b1.assign_sub(lr *grads[3])
        b2.assign_sub(lr *grads[4])
        b3.assign_sub(lr *grads[5])

        if step % 100 == 0:
            print(step, 'loss', float(loss))