吴裕雄--天生自然TensorFlow2教程：损失函数及其梯度

import tensorflow as tf

x = tf.random.normal([2, 4])
w = tf.random.normal([4, 3])
b = tf.zeros([3])
y = tf.constant([2, 0])

with tf.GradientTape() as tape:
    tape.watch([w, b])
    prob = tf.nn.softmax(x @ w + b, axis=1)
    loss = tf.reduce_mean(tf.losses.MSE(tf.one_hot(y, depth=3), prob))

grads = tape.gradient(loss, [w, b])
grads[0]

x = tf.random.normal([2, 4])
w = tf.random.normal([4, 3])
b = tf.zeros([3])
y = tf.constant([2, 0])

with tf.GradientTape() as tape:
    tape.watch([w, b])
    logits =x @ w + b
    loss = tf.reduce_mean(
        tf.losses.categorical_crossentropy(tf.one_hot(y, depth=3),logits,from_logits=True))

grads = tape.gradient(loss, [w, b])
grads[0]