tensorflow函数解析：Session.run和Tensor.eval的区别

tensorflow函数解析：Session.run和Tensor.eval

翻译 2017年04月20日 15:05:50

• 标签：
• tensorflow /
• 机器学习 /
• 深度学习 /
• python

• 7774

原问题连接：

http://stackoverflow.com/questions/33610685/in-tensorflow-what-is-the-difference-between-session-run-and-tensor-eval

译：

问题：

tensorflow有两种方式：Session.run和 Tensor.eval，这二者的区别在哪？

答：

若是你有一个Tensor t，在使用t.eval()时，等价于：tf.get_default_session().run(t).

举例：

 

t = tf.constant(42.0) sess = tf.Session() with sess.as_default(): # or `with sess:` to close on exit assert sess is tf.get_default_session() assert t.eval() == sess.run(t)

 

这其中最主要的区别就在于你能够使用sess.run()在同一步获取多个tensor中的值，

例如：

 

t = tf.constant(42.0) u = tf.constant(37.0) tu = tf.mul(t, u) ut = tf.mul(u, t) with sess.as_default(): tu.eval() # runs one step ut.eval() # runs one step sess.run([tu, ut]) # evaluates both tensors in a single step

 

注意到：每次使用 eval 和 run时，都会执行整个计算图，为了获取计算的结果，将它分配给tf.Variable，而后获取。

原文以下：

Question：

TensorFlow has two ways to evaluate part of graph: Session.run on a list of variables and Tensor.eval. Is there a difference between these two?

Answer：

If you have a Tensor t, calling t.eval() is equivalent to calling tf.get_default_session().run(t).

You can make a session the default as follows:

t = tf.constant(42.0) sess = tf.Session() with sess.as_default(): # or `with sess:` to close on exit assert sess is tf.get_default_session() assert t.eval() == sess.run(t)

The most important difference is that you can use sess.run() to fetch the values of many tensors in the same step:

t = tf.constant(42.0) u = tf.constant(37.0) tu = tf.mul(t, u) ut = tf.mul(u, t) with sess.as_default(): tu.eval() # runs one step ut.eval() # runs one step sess.run([tu, ut]) # evaluates both tensors in a single step

Note that each call to eval and run will execute the whole graph from scratch. To cache the result of a computation, assign it to a tf.Variable.