Tzu-Wei Sung

> The former can be done. The latter, however, will cause the code to slow down further, since it would independently address each piece along each axis (O(n^3)). Independent loops...

Sounds great! Free feel to file an PR. Also, our style is a little bit different from the one of core TF so please take a look at https://github.com/tensorflow/addons/blob/master/CONTRIBUTING.md. But...

> Hey @AakashKumarNain @facaiy @WindQAQ thanks for the suggestions! I'm working on the [layer version](https://github.com/crystina-z/addons/blob/feature/mixout_layer/tensorflow_addons/layers/mixout.py) but then realize it's actually hard since `Mixout` requires to manipulate the weight in the...

Hi @AlexeyKurakin, is anyone working on this? If not, I would like to do this. Thanks!

Sure! Want to make sure something here: 1. do we need to decorate the tests with [run_all_in_graph_and_eager_modes](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/framework/test_util.py#L915) to make them compatible with graph mode? 2. should we inherit the tests...

Thanks you! I would create a PR for fast_gradient_method first to let you see if it is good enough.

> Regarding #1, we had a discussion with @AlexeyKurakin and our current stand is that we should aim to verify the possibility of wrapping all attack functions in @tf.function in...

Hi @laurensnaturalis, could you provide the minimal runnable code snippet so that we could diagnose where the problem is easily? Thank you!

Hi @pstjohn, thanks for the report. It would be great if you could provide a minimal code snippet about `MultiWorkerMirroredStrategy` so that we can diagnose where the problem is!

Hi @pstjohn, thanks for the update! Unfortunately, I currently do not have the access to multi-nodes and multi-GPUs machines. Is it possible to attach the full log file as well?...