tf.control_dependencies()
有些机器学习程序中我们想要指定某些操作执行的依赖关系,这时我们可以使用tf.control_dependencies()
来实现。control_dependencies(control_inputs)
返回一个控制依赖的上下文管理器,使用with
关键字可以让在这个上下文环境中的操作都在control_inputs
执行。
with g.control_dependencies([a, b, c]):
# `d` and `e` will only run after `a`, `b`, and `c` have executed.
d = ...
e = ...
可以传入None
来消除依赖:
with g.control_dependencies([a, b]):
# Ops constructed here run after `a` and `b`.
with g.control_dependencies(None):
# Ops constructed here run normally, not waiting for either `a` or `b`.
with g.control_dependencies([c, d]):
# Ops constructed here run after `c` and `d`, also not waiting
# for either `a` or `b`.
注意:
控制依赖只对那些在上下文环境中建立的操作有效,仅仅在context中使用一个操作或张量是没用的
# WRONG
def my_func(pred, tensor):
t = tf.matmul(tensor, tensor)
with tf.control_dependencies([pred]):
# The matmul op is created outside the context, so no control
# dependency will be added.
return t
# RIGHT
def my_func(pred, tensor):
with tf.control_dependencies([pred]):
# The matmul op is created in the context, so a control dependency
# will be added.
return tf.matmul(tensor, tensor)
tf.identify()
https://blog.csdn.net/hu_guan_jie/article/details/78495297
把tf.Variable变为tf.Tensor
import tensorflow as tf
x = tf.Variable(0.0)
x_plus = tf.assign_add(x, 1)
with tf.control_dependencies([x_plus]):#只有当内部为操作时以来才会生效
y = tf.identity(x)#将该语句变为操作
init = tf.global_variables_initializer()
with tf.Session() as session:
init.run()
for i in range(5):
print(y.eval())
print(x.eval())#5
tf.group()
import tensorflow as tf
x = tf.Variable(0.0)
x_plus = tf.assign_add(x, 1)
with tf.control_dependencies([x_plus]):#只有当内部为操作时以来才会生效
#y = tf.identity(x)#将该语句变为操作
y = x
update = tf.group(y)#将该语句变为操作
init = tf.global_variables_initializer()
with tf.Session() as session:
init.run()
for i in range(5):
session.run(update)
print(y.eval())
print(x.eval())#5