TensorFlow基本操作7

重点函数

tf.data.Dataset.from_tensor_slices((x,y)).batch(128)
tf.one_hot(y,depth=10)
原地修改数据：w1.assign_sub(lr * grads[0])

10 前向传播实战

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

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

x = tf.convert_to_tensor(x,dtype=tf.float32)
y = tf.convert_to_tensor(y,dtype=tf.int32)

print(x.shape,y.shape)
print(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(sample[0].shape, sample[1].shape)


# input 28*28 = 784
w1 = tf.Variable(tf.random.truncated_normal([784, 256],stddev=0.01))
b1 = tf.Variable(tf.zeros([256]))

w2 = tf.Variable(tf.random.truncated_normal([256, 128],stddev=0.01))
b2 = tf.Variable(tf.zeros([128]))

w3 = tf.Variable(tf.random.truncated_normal([128, 10],stddev=0.01))
b3 = tf.Variable(tf.zeros([10]))

lr = 0.0001
epoches = 10

for epoch in range(epoches):

    for step , (x,y) in enumerate(train_db):
        x = tf.reshape(x, [-1, 28*28])

        with tf.GradientTape() as tape:
            h1 = x@w1 + tf.broadcast_to(b1, [x.shape[0], 256])
            h1 = tf.nn.relu(h1)

            h2 = h1 @ w2 + b2
            h2 = tf.nn.relu(h2)

            out = h2 @ w3 + b3

            y_onehot = tf.one_hot(y,depth=10)

            loss = tf.square(y_onehot - out)
            loss = tf.reduce_mean(loss)

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

        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:',epoch, 'step:' ,step, 'loss:', float(loss))

1.为什么 2.0 了，还需要用 tf.Variable() 把变量包装起来呢？