📜  Python – tensorflow.GradientTape.stop_recording()

📅  最后修改于: 2022-05-13 01:54:26.279000             🧑  作者: Mango

Python – tensorflow.GradientTape.stop_recording()

TensorFlow 是由 Google 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。

stop_recording()用于暂时停止录制操作。如果磁带未录制,则会引发错误。

示例 1:

Python3
# Importing the library
import tensorflow as tf
  
x = tf.constant(4.0)
  
# Using GradientTape
with tf.GradientTape() as gfg:
  gfg.watch(x)
  
  # Stop recording
  with gfg.stop_recording():
    y = x * x * x
  
# Computing gradient
res = gfg.gradient(y, x) 
  
# Printing result
print("res: ", res)


Python3
# Importing the library
import tensorflow as tf
  
x = tf.constant(4.0)
  
# Using GradientTape
with tf.GradientTape() as gfg:
  gfg.watch(x)
  
  # Stop recording
  with gfg.stop_recording():
    y = x * x * x
  
  # Starting the recording again
  gfg.watch(x)
  y = x * x
  
# Computing gradient
res = gfg.gradient(y, x) 
  
# Printing result
print("res: ", res)


输出:

res:  None

示例 2:

Python3

# Importing the library
import tensorflow as tf
  
x = tf.constant(4.0)
  
# Using GradientTape
with tf.GradientTape() as gfg:
  gfg.watch(x)
  
  # Stop recording
  with gfg.stop_recording():
    y = x * x * x
  
  # Starting the recording again
  gfg.watch(x)
  y = x * x
  
# Computing gradient
res = gfg.gradient(y, x) 
  
# Printing result
print("res: ", res)

输出:

res:  tf.Tensor(8.0, shape=(), dtype=float32)