Python – tensorflow.GradientTape.batch\_jacobian()

TensorFlow是谷歌设计的开源Python库，用于开发机器学习模型和深度学习神经网络。

batch\_jacobian()用于计算和堆积每个例子的jacobian。

语法:
batch_jacobian( target, source, unconnected_gradients, parallel_iterations, experimental_use_pfor )

参数:

• target：它是一个最小等级为2的张量。
• source: 它是一个具有最小等级2的张量。
• unconnected\_gradients（可选）:它的值可以是零或无。默认值是无。
• parallel\_iterations（可选）: 它用于控制并行迭代和内存使用。
• experimental\_use\_pfor（可选）: 它是一个布尔值，默认值为True。当设置为True时，它使用pfor来计算Jacobian，否则就使用 tf.while\_loop。

返回：它返回一个张量。

示例 1:

# Importing the library
import tensorflow as tf

x = tf.constant([[4, 2],[1, 3]], dtype=tf.dtypes.float32)

# Using GradientTape
with tf.GradientTape() as gfg:
  gfg.watch(x)
  y = x * x * x

# Computing jacobian
res  = gfg.batch_jacobian(y, x) 

# Printing result
print("res: ",res)

输出:

res: tf.Tensor(
[[[48. 0.]
[ 0. 12.]]

[[ 3. 0.]
[ 0. 27.]]], shape=(2, 2, 2), dtype=float32)

示例 2:

# Importing the library
import tensorflow as tf

x = tf.constant([[4, 2],[1, 3]], dtype=tf.dtypes.float32)

# Using GradientTape
with tf.GradientTape() as gfg:
  gfg.watch(x)

  # Using nested GradientTape for calculating higher order jacobian
  with tf.GradientTape() as gg:
    gg.watch(x)
    y = x * x * x
  # Computing first order jacobian
  first_order = gg.batch_jacobian(y, x)

# Computing Second order jacobian
second_order  = gfg.batch_jacobian(first_order, x) 

# Printing result
print("first_order: ",first_order)
print("second_order: ",second_order)

输出:

first_order: tf.Tensor(
[[[48. 0.]
[ 0. 12.]]

[[ 3. 0.]
[ 0. 27.]]], shape=(2, 2, 2), dtype=float32)
second_order: tf.Tensor(
[[[[24. 0.]
[ 0. 0.]]

[[ 0. 0.]
[ 0. 12.]]]


[[[ 6. 0.]
[ 0. 0.]]

[[ 0. 0.]
[ 0. 18.]]]], shape=(2, 2, 2, 2), dtype=float32)