欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

TensorFlow Autodiff自动微分

程序员文章站 2022-07-12 23:15:26
...
with tf.GradientTape(persistent=True) as tape:
    z1 = f(w1, w2 + 2.)
    z2 = f(w1, w2 + 5.)
    z3 = f(w1, w2 + 7.)
    z = [z1,z3,z3]
[tape.gradient(z, [w1, w2]) for z in (z1, z2, z3)]

输出结果

[[<tf.Tensor: id=56906, shape=(), dtype=float32, numpy=40.0>,
  <tf.Tensor: id=56898, shape=(), dtype=float32, numpy=10.0>],
 [<tf.Tensor: id=56919, shape=(), dtype=float32, numpy=46.0>,
  <tf.Tensor: id=56911, shape=(), dtype=float32, numpy=10.0>],
 [<tf.Tensor: id=56932, shape=(), dtype=float32, numpy=50.0>,
  <tf.Tensor: id=56924, shape=(), dtype=float32, numpy=10.0>]]
with tf.GradientTape(persistent=True) as tape:
    z1 = f(w1, w2 + 2.)
    z2 = f(w1, w2 + 5.)
    z3 = f(w1, w2 + 7.)
    z = [z1,z2,z3]
tape.gradient(z, [w1, w2])

输出结果

[<tf.Tensor: id=57075, shape=(), dtype=float32, numpy=136.0>,
 <tf.Tensor: id=57076, shape=(), dtype=float32, numpy=30.0>]

总结:如果对一个listz=[z1,z2,z3]求微分,其结果将自动求和,而不是返回z1z2z3各自对[w1,w2]的微分。

相关标签: TensorFlow/Keras