[英]TensorFlow session run graph defined outside under tf.Graph()
When initializing tf.Session()
, we can pass in a graph like tf.Session(graph=my_graph)
, for example: 初始化tf.Session()
,我们可以传入像tf.Session(graph=my_graph)
这样的tf.Session(graph=my_graph)
,例如:
import tensorflow as tf
# define graph
my_graph = tf.Graph()
with my_graph.as_default():
a = tf.constant(100., tf.float32, name='a')
# run graph
with tf.Session(graph=my_graph) as sess:
a = sess.graph.get_operation_by_name('a')
print(sess.run(a)) # prints None
In the example above, it prints None
. 在上面的示例中,它打印None
。 How can we execute an operation defined inside my_graph
? 我们如何执行my_graph
定义的操作?
This is the intended behavior, but I can see why it would be surprising! 这是预期的行为,但我可以看出为什么会令人惊讶! The following line returns a tf.Operation
object: 以下行返回tf.Operation
对象:
a = sess.graph.get_operation_by_name('a')
...and when you pass a tf.Operation
object to Session.run()
, TensorFlow will execute the operation, but it will discard its outputs and return None
. ...当您将tf.Operation
对象传递给Session.run()
,TensorFlow将执行该操作,但它将丢弃其输出并返回None
。
The following program probably has the behavior you're expecting, by explicitly specifying the 0th output of that operation and retrieving a tf.Tensor
object: 以下程序可能具有您期望的行为,方法是显式指定该操作的第0个输出并检索tf.Tensor
对象:
with tf.Session(graph=my_graph) as sess:
a = sess.graph.get_operation_by_name('a').outputs[0]
# Or you could do:
# a = sess.graph.get_tensor_by_name('a:0')
print(sess.run(a)) # prints '100.'
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.