TensorFlow是Google設計的開源Python庫,用於開發機器學習模型和深度學習神經網絡。
stop_recording()用於暫時停止記錄操作。如果磁帶未在錄製,則會引發錯誤。
用法:tensorflow.GradientTape.stop_recording()
參數:它不接受任何參數。
返回:空
raise :
- RunTimeError:如果磁帶沒有及時錄製,它將引發RunTimeError。
範例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)
輸出:
res: None
範例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)
輸出:
res: tf.Tensor(8.0, shape=(), dtype=float32)
相關用法
注:本文由純淨天空篩選整理自aman neekhara大神的英文原創作品 Python – tensorflow.GradientTape.stop_recording()。非經特殊聲明,原始代碼版權歸原作者所有,本譯文未經允許或授權,請勿轉載或複製。