python实现前向传播（张量）

python实现前向传播（张量）

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

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
# x:[60k, 28, 28]
# y:[60k]
(x, y), _ = datasets.mnist.load_data()
# 转换为张量,将x范围从[0-255] => [0-1.]
x = tf.convert_to_tensor(x, dtype=tf.float32) / 255.
y = tf.convert_to_tensor(y, dtype=tf.int32)
# 查看x,y的数据类型
# print(x.shape, y.shape, x.dtype, y.dtype)
# 查看x,y的最大值和最小值
# print(tf.reduce_min(x), tf.reduce_max(x))
# print(tf.reduce_min(y), tf.reduce_max(y))
# 取出一定量的数据，这里一次取出128个
train_db = tf.data.Dataset.from_tensor_slices((x, y)).batch(128)
# 定义迭代器去循环这些数据
train_iter = iter(train_db)
# 依次取出数据
sample = next(train_iter)
# print('batch:', sample[0].shape, sample[1].shape)

# [b, 784] => [b, 512] => [b, 10]
# [dim_in, dim_out], [dim_out], 将方差定为一个比较小的数，防止梯度爆炸
w1 = tf.Variable(tf.random.truncated_normal([784, 256], stddev=0.1))
# 这里的256就是前一步的输出维度
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

# 对整个数据集迭代10次
for epoch in range(10):
    # 对当前的一次循环迭代step次
    for step, (x, y) in enumerate(train_db):
        # x:[128,28,28]
        # y:[128]

        # 维度转换
        # [b,28,28] = > [b, 28*28]
        x = tf.reshape(x, [-1, 28*28])
        # print(x.shape)

        # 只有类型是Variable的数据才会被记录
        with tf.GradientTape() as tape:
            # x:[b, 28*28]
            # h1 = x@w1 + b1
            # [b, 784]@[784,256] + [256} => [b, 256] + [256]
            h1 = x@w1 + b1
            h1 = tf.nn.relu(h1)
            # [b, 256] => [b, 128]
            h2 = h1@w2 + b2
            h2 = tf.nn.relu(h2)
            # [b, 128] => [b, 10]
            out = h2@w3 + b3

            # compute loss
            # out: [b, 10]
            # y: [b]
            y_onehot = tf.one_hot(y, depth=10)

            # mse = mean(sum(y-out)^2)
            # [b, 10]
            loss = tf.square(y_onehot - out)
            # mean: scalar
            loss = tf.reduce_mean(loss)
        grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3])
        # w1 = w1 - lr * w1_grad
        w1.assign_sub(lr * grads[0])
        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])

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