TesorFlow03.1-TesorFlow基础实战（前向传播（张量））

在前面已经学习了：
What we have learned
▪ create tensor
▪ indexing and slices
▪ reshape and broadcasting
▪ math operations

现在用tensorFlow做一个前向传播的一个小实战:

1.加载数据

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

import  os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'

#加载数据集
#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.dtype)
print(tf.reduce_min(x), tf.reduce_max(x))
print(tf.reduce_min(y), tf.reduce_max(y))

我们会发现这个x最小是0，最大是255，但是我们除了255，所以是[0-1],y是[0-9]

定义相关参数

# [b, 784] => [b, 256] => [b, 128] => [b, 10]
# [dim_in, dim_out], [dim_out]
#这里要定义成Variable ，因为后面求偏导数的时候要跟踪他的梯度
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]))

这里要注意，w1,w2,w3,b1,b2,b3要定义成Variable类型，因为后面求偏导数的时候要跟踪他的梯度

梯度下降

lr = 1e-3

losses = []

for epoch in range(20): # iterate db for 10，也就是多迭代几次
    for step, (x, y) in enumerate(train_db): # for every batch
        # x:[128, 28, 28]
        # y: [128]

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

        with tf.GradientTape() as tape: # tf.Variable
            # 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] => [b, 10]
            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)

        # compute gradients
        grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3])
        # print(grads)
        # 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))

    losses.append(float(loss))

这里要注意的是w1.assign_sub()，是为了保证w1还是Variable类型，进行相减