Mohammed Innat

> What I meant is that shufflenet has not this randomizzation requirements so probably we need to do something different. Like this? ```python tf.random.set_seed(self.seed) tf.random.uniform(shape=[self.group], seed=self.seed) ```

Yes. I found that earlier but couldn't adopt it because initially this layer was proposed as an input channel shuffle and randomness was a must. However, now I think we...

@bhack > I think we could separate Shuffle in Shufflenet and KLP layers as they have two very different behaviors. The operation will have a subtle difference if we want...

> > What I meant is that shufflenet has not this randomizzation requirements so probably we need to do something different. > > Like this? > > ```python > tf.random.set_seed(self.seed)...

@bhack > Correct me if I am wrong. By an API point of view as our KLP layers are preprocessing layers they are not guaranteed do be differentiable. So it...

@bhack cc. @LukeWood > Also If we consider this a quite rare case (I am not so future proof on this), for the API consistency we need to consider that...

@anish9 would you mind sharing a colab file of your contribution? It'd be useful.

> > @anish9 would you mind sharing a colab file of your contribution? It'd be useful. > > @innat [colab.research.google.com/drive/1KOEc1Zkeo9EUfeOILcBb-so9FV4v6LB3?usp=sharing](https://colab.research.google.com/drive/1KOEc1Zkeo9EUfeOILcBb-so9FV4v6LB3?usp=sharing) @anish9 I couldn't successfully run your code on colab (GPU)....

@anish9 I tried to run the colab on GPU. But for it takes too much time to complete per epoch (~500s). Is it expected?

@anish9 Thanks for making this nice tutorial on such a challenging problem. I can relate. It would be a nice starter for the interested practitioners in the OCR domain. And...