tensorflow(十一)：前向传播实战——三层神经网络

一、神经网络设计

𝑜𝑢𝑡 = 𝑟𝑒𝑙𝑢{𝑟𝑒𝑙𝑢 𝑟𝑒𝑙𝑢 𝑋@𝑊1 + 𝑏1 @𝑊2 + 𝑏2 @𝑊3 + 𝑏3

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import datasets
#x:[60k, 28, 28]
#y:[60K]
(x,y),_ = datasets.mnist.load_data()
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.shape)
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]
#w[dim_in, dim_out], b[dim_out]
#要自动求导的值必须是Varible, 不设置方差会出现梯度离散
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]
        #[b,28,28] => [b, 28*28]
        x = tf.reshape(x, [-1, 28*28])
        with tf.GradientTape() as tape:
            #这是梯度更新的部分
            # x:[b,28*28]
            # h1 = x@w1+b1
            # [b, 784]@[784, 256] + [256] => [b, 256] + [256] => [b, 256] + [b, 256]
            h1 = x@w1 + tf.broadcast_to(b1, [x.shape[0], 256])
            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)
            loss = tf.square(y_onehot - out)
            #mean:scalar
            #函数用于计算张量tensor沿着指定的数轴（tensor的某一维度）上的的平均值
            loss = tf.reduce_mean(loss)
        # compute gradients
        grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3])
        # w1 = w1 -lr * w1_grad
        #相减之后成了tensor,不是Varible，所以不能相减
        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))