运行时错误:tf.placeholder() 与急切执行不兼容

问题描述

我已将 tf_upgrade_v2 TF1 代码升级到 TF2.我对两者都是菜鸟.我收到下一个错误:

I have upgraded with tf_upgrade_v2 TF1 code to TF2. I'm a noob with both. I got the next error:

RuntimeError: tf.placeholder() is not compatible with eager execution.

我有一些 tf.compat.v1.placeholder().

self.temperature = tf.compat.v1.placeholder_with_default(1., shape=())
self.edges_labels = tf.compat.v1.placeholder(dtype=tf.int64, shape=(None, vertexes, vertexes))
self.nodes_labels = tf.compat.v1.placeholder(dtype=tf.int64, shape=(None, vertexes))
self.embeddings = tf.compat.v1.placeholder(dtype=tf.float32, shape=(None, embedding_dim))

你能给我一些关于如何进行的建议吗?任何快速"解决方案?还是我应该重新编码?

Could you give me any advice about how to proceed? Any "fast" solutions? or should I to recode this?

推荐答案

我在这里找到了一个简单的解决方案:禁用 Tensorflow 急切执行

I found an easy solution here: disable Tensorflow eager execution

基本上是:

tf.compat.v1.disable_eager_execution()

使用此功能，您可以禁用默认的激活急切执行，并且您无需更多地接触代码.

With this, you disable the default activate eager execution and you don't need to touch the code much more.

这篇关于运行时错误:tf.placeholder() 与急切执行不兼容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！