ValueError:密集层的输入0与该层不兼容:其等级未定义，但是该层需要一个已定义的等级 [英] ValueError: Input 0 of layer dense is incompatible with the layer: its rank is undefined, but the layer requires a defined rank

问题描述

在> https://www.tensorflow.org/tutorials/images/上尝试该示例时使用tf '2.0.0-alpha0'的本地计算机上的hub_with_keras (下载，pip-下载hub '0.4.0-dev'并删除!pip...行，安装tf 2，删除enable_v2_behavior ，运行文件)，则失败，

When trying the example at https://www.tensorflow.org/tutorials/images/hub_with_keras at a local computer with tf '2.0.0-alpha0' (download, pip-download hub '0.4.0-dev' and remove !pip... lines, install tf 2, remove enable_v2_behavior , run file), it failed with

ValueError:密集层的输入0与该层不兼容:其等级未定义，但是该层需要一个已定义的等级.

ValueError: Input 0 of layer dense is incompatible with the layer: its rank is undefined, but the layer requires a defined rank.

它在Google colab上运行良好.为什么会这样，如何解决?

It runs fine on Google colab though. Why is this and how can it be fixed?

推荐答案

如@arnoegw在评论中所建议，此问题已在tf-nightly-2.0-preview中修复.因此，直到它投入生产之前，只需使用

As proposed by @arnoegw in the comments, this is fixed in tf-nightly-2.0-preview. So until it lands in production, just use

pip install tf-nightly-2.0-preview

这篇关于ValueError:密集层的输入0与该层不兼容:其等级未定义，但是该层需要一个已定义的等级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！