TensorFlow2_200729系列---13、二阶梯度求解

TensorFlow2_200729系列---13、二阶梯度求解

一、总结

一句话总结：

梯度是放在with tf.GradientTape() as t1 语句之中，那二阶梯度就是这个语句的嵌套

import tensorflow as tf

w = tf.Variable(1.0)
b = tf.Variable(2.0)
x = tf.Variable(3.0)

with tf.GradientTape() as t1:
  with tf.GradientTape() as t2:
    y = x * w + b
  dy_dw, dy_db = t2.gradient(y, [w, b])
d2y_dw2 = t1.gradient(dy_dw, w)

print(dy_dw)
print(dy_db)
print(d2y_dw2)

assert dy_dw.numpy() == 3.0
assert d2y_dw2 is None

 

 

二、二阶梯度求解

博客对应课程的视频位置：

 

import tensorflow as tf

w = tf.Variable(1.0)
b = tf.Variable(2.0)
x = tf.Variable(3.0)

with tf.GradientTape() as t1:
  with tf.GradientTape() as t2:
    y = x * w + b
  dy_dw, dy_db = t2.gradient(y, [w, b])
d2y_dw2 = t1.gradient(dy_dw, w)

print(dy_dw)
print(dy_db)
print(d2y_dw2)

assert dy_dw.numpy() == 3.0
assert d2y_dw2 is None

tf.Tensor(3.0, shape=(), dtype=float32)
tf.Tensor(1.0, shape=(), dtype=float32)
None