链式法则
作者:互联网
目录
- Derivative Rules
- Chain rule
Derivative Rules
Chain rule
import tensorflow as tf
x = tf.constant(1.) w1 = tf.constant(2.) b1 = tf.constant(1.) w2 = tf.constant(2.) b2 = tf.constant(1.) with tf.GradientTape(persistent=True) as tape: tape.watch([w1, b1, w2, b2]) y1 = x * w1 + b1 y2 = y1 * w2 + b2 dy2_dy1 = tape.gradient(y2, [y1])[0] dy1_dw1 = tape.gradient(y1, [w1])[0] dy2_dw1 = tape.gradient(y2, [w1])[0] dy2_dy1 * dy1_dw1
<tf.Tensor: id=132, shape=(), dtype=float32, numpy=2.0>
dy2_dw1
<tf.Tensor: id=138, shape=(), dtype=float32, numpy=2.0>
标签:链式法则,constant,dy1,y1,tape,w1,tf 来源: https://blog.51cto.com/u_13804357/2709151