如何禁用 TensorFlow 的急切执行?

本文介绍了如何禁用 TensorFlow 的急切执行?的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！

问题描述

限时送ChatGPT账号..

我正在尝试学习 TensorFlow.目前，我正在使用占位符.当我尝试创建占位符时，出现错误:RuntimeError: tf.placeholder() is not compatible with Eager execution，这是有道理的，因为占位符不能立即执行.

I am trying to learn TensorFlow. Currently, I am working with placeholders. When I tried to create the placeholder, I got an error: RuntimeError: tf.placeholder() is not compatible with eager execution, which makes sense as placeholders are not executable immediately.

那么，如何关闭急切执行?

So, how do I turn eager execution off?

我从一开始就没有开启 Eager Execution，所以我不确定它是怎么发生的.有没有与 tf.disable_eager_execution() 相对的?

I have never turned eager execution on in the first place, so I am not sure how it happened. Is there an opposite to tf.disable_eager_execution()?

推荐答案

假设您使用的是 Tensorflow 2.0 预览版，它默认启用了 Eager Execution.v1 API 中有一个 disable_eager_execution()，你可以把它放在你的代码前面，比如:

Assume you are using Tensorflow 2.0 preview release which has eager execution enabled by default. There is a disable_eager_execution() in v1 API, which you can put in the front of your code like:

import tensorflow as tf

tfpat.v1.disable_eager_execution()

另一方面，如果您没有使用 2.0 预览版，请检查您是否不小心在某处启用了 Eager Execution.

On the other hand, if you are not using 2.0 preview, please check if you accidentally enabled eager execution somewhere.

这篇关于如何禁用 TensorFlow 的急切执行?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！