Example: Scalars (multivariate) (Personal website)

Up: Automatic differentiation with GradientTape [Top][Contents]

Example: Scalars (multivariate)

Evaluate \(y = a^2 + b\) at \(a = 10\) and \(b = 20\).
Find \(\dv*{y}{a}\) and \(\dv*{y}{b}\) at said \(a\) and \(b\).

import tensorflow as tf

a = tf.constant(10.0)
b = tf.constant(20.0)

with tf.GradientTape() as tape:
    tape.watch([a, b])
    y = a ** 2 + b

da, db = tape.gradient(y, [a, b])

f"y = {y}, dy/da = {da}, dy/db = {db}"

y = 120.0, dy/da = 20.0, dy/db = 1.0