Pruning error for transfer learning models from TF/Keras API

System information

TensorFlow version (installed from source or binary): 2.10

TensorFlow Model Optimization version (installed from source or binary): 0.7.3

Python version: 3.8

Bug

Hi,

I have been experimenting with ILSVRC2012 lately, and tried pruning pre-trained models that I took from the Keras/TF API. I used the pruning examples from the tfmopt documentation and it worked well for my "homemade" NNs as well as Nasnet NNs. However, with all the other ones I tried (I did not try each and every one of them but still), I got the following error

ValueError: Please initialize Prunewith a supported layer. Layers should either be supported by the PruneRegistry (built-in keras layers) or should be aPrunableLayerinstance, or should has a customer definedget_prunable_weights method. You passed: <class 'keras.layers.preprocessing.image_preprocessing.Rescaling'>

It apparently should have been fixed by this PR, yet, well, here we are. It seems I am not the only one who had this problem.

You can find the code I used on this colab. I included an example that worked for reference's purpose.

Thank you for your time !