在 TensorFlow 中，Session.run() 和 Tensor.eval() 有什么区别? [英] In TensorFlow, what is the difference between Session.run() and Tensor.eval()?

问题描述

TensorFlow 有两种方法来评估图的一部分:Session.run 在变量列表上和 Tensor.eval.这两者有区别吗?

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?

推荐答案

如果你有一个 Tensor t，调用 t.eval() 相当于调用 tf.get_default_session().run(t).

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

您可以将会话设为默认值，如下所示:

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)

最重要的区别是您可以使用 sess.run() 在同一步骤中获取许多张量的值:

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

请注意，每次调用 eval 和 run 都会从头开始执行整个图.要缓存计算结果，请将其分配给 tf.Variable.

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.

这篇关于在 TensorFlow 中，Session.run() 和 Tensor.eval() 有什么区别?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！