Mohammed Innat

> The 4th page of the paper states > > > The pooling parameter pk can be manually set or learned since this operation is differentiable and can be part...

Any update on this?

> This sounds reasonable and the citation count is sufficient to consider inclusion. GeMPooling*D seems like a better name. The suggested layer name is reasonable to choose. But I'm wondering...

@sushreebarsa Thanks for running the test. You're using `tf 2.9`. I tried to run your gist with GPU, and I got ``` --------------------------------------------------------------------------- UnimplementedError Traceback (most recent call last) [](https://localhost:8080/#)...

The error message with CPU mode training, ``` Unimplemented `tf.keras.Model.call()`: if you intend to create a `Model` with the Functional API, please provide `inputs` and `outputs` arguments. Otherwise, subclass `Model`...

@sushreebarsa I made another ticket regarding this behavior. Please check https://github.com/keras-team/keras/issues/16662 > Could you please find the gist [here](https://colab.research.google.com/gist/sushreebarsa/d9651608ea4f1e6433bf9a4d8cfe4db0/16654.ipynb) and let me know if I am missing something to reproduce...

So, the conclusion is, that this is a bug for `tf 2.8`. And it's fixed in `tf 2.9` but at reloading time, we need to use `custom_objects`. With `tf 2.9`...

cc. @awsaf49 Cutmix is available officially in `keras`, [HERE](https://github.com/keras-team/keras-cv/blob/master/keras_cv/layers/preprocessing/cut_mix.py). The Mosaic one will be soon.

@qubvel would you please look into this. It's kinda important. Mixed precision training falls without this fix.

In the meantime, if anyone who looking for UNet++ (aka, XNet) in `tf.keras`. Here, [XNet-TF.Keras](https://gist.github.com/innat/2d2fd2e93b47dd5349095182eb984ef6). [Discussion. ](https://github.com/MrGiovanni/UNetPlusPlus/issues/77)