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: Input 0 of layer dense is incompatible with the layer: its rank is undefined, but the layer requires a defined rank.
It runs fine on Google colab though. Why is this and how can it be fixed?
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