Python tensorflow 中的 eval() 和 run()
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/38987466/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
eval() and run() in tensorflow
提问by Ramesh-X
I'm referring to Deep MNIST for Experts tutorialgiven by the tensorflow. I have a problem in Train and Evaluatepart of that tutorial. There they have given a sample code as follows.
我指的是tensorflow给出的Deep MNIST for Experts 教程。我在该教程的训练和评估部分遇到了问题。他们在那里给出了一个示例代码，如下所示。
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv),reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
sess.run(tf.initialize_all_variables())
for i in range(20000):
batch = mnist.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print("test accuracy %g"%accuracy.eval(feed_dict={x: mnist.test.images,
y_: mnist.test.labels, keep_prob: 1.0}))
So in these code segment they have used accuracy.eval()at one time. And other time train_step.run(). As I know of both of them are tensor variables.
所以在这些代码段中他们曾经使用accuracy.eval()过一次。和其他时间train_step.run()。据我所知，它们都是张量变量。
And in some cases, I have seen like
在某些情况下，我看到像
sess.run(variable, feed_dict)
So my question is what are the differences between these 3 implementations. And how can I know what to use when..?
所以我的问题是这 3 个实现之间有什么区别。我怎么知道什么时候用..？
Thank You!!
谢谢你！！
回答by fwalch
If you have only one default session, they are basically the same.
如果您只有一个默认会话，则它们基本相同。
From https://github.com/tensorflow/tensorflow/blob/v1.12.0/tensorflow/python/framework/ops.py#L2351:
从https://github.com/tensorflow/tensorflow/blob/v1.12.0/tensorflow/python/framework/ops.py#L2351：
op.run() is a shortcut for calling tf.get_default_session().run(op)
op.run() 是调用 tf.get_default_session().run(op) 的快捷方式
From https://github.com/tensorflow/tensorflow/blob/v1.12.0/tensorflow/python/framework/ops.py#L691:
从https://github.com/tensorflow/tensorflow/blob/v1.12.0/tensorflow/python/framework/ops.py#L691：
t.eval() is a shortcut for calling tf.get_default_session().run(t)
t.eval() 是调用 tf.get_default_session().run(t) 的快捷方式
Difference between Tensor and Operation:
张量和运算的区别：
Tensor: https://www.tensorflow.org/api_docs/python/tf/Tensor
张量：https: //www.tensorflow.org/api_docs/python/tf/Tensor
Operation: https://www.tensorflow.org/api_docs/python/tf/Operation
操作：https: //www.tensorflow.org/api_docs/python/tf/Operation
Note: the Tensor class will be replaced by Output in the future. Currently these two are aliases for each other.
注意：Tensor 类将来会被 Output 替换。目前这两个是彼此的别名。
回答by idnavid
The difference is in Operations vs. Tensors. Operations use run() and Tensors use eval().
区别在于操作与张量。操作使用 run()，张量使用 eval()。
There seems to be a reference to this question in TensorFlow FAQ: https://www.tensorflow.org/programmers_guide/faq#running_a_tensorflow_computation
TensorFlow FAQ 中似乎有对这个问题的引用：https://www.tensorflow.org/programmers_guide/faq#running_a_tensorflow_computation
The section addresses the following question: What is the difference between Session.run() and Tensor.eval()?
该部分解决了以下问题：Session.run() 和 Tensor.eval() 之间有什么区别？
