Feature Request: TCN Layer (temporal convolutional networks)

[shun-lin]

Describe the feature and the current behavior/state.

The feature is for adding the different layers introduced in An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling paper to tfa.layers. There is already existed an Keras implementation here: https://github.com/philipperemy/keras-tcn/, I feel like this is helpful and would have more visibility in tfa so I ask him in this issue if I can help out porting the TCN layers portion into tfa and he says yes :)
If you feel like this would be a good addition let me know, very happy to contribute.

Relevant information

• Are you willing to contribute it (yes/no): yes of course :)
• Are you willing to maintain it going forward? (yes/no): yes of course :)
• Is there a relevant academic paper? (if so, where): yes An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Is there already an implementation in another framework? (if so, where):
  No but was implemented in pytorch in this repo, https://github.com/locuslab/TCN, and Keras in this repo https://github.com/philipperemy/keras-tcn (will be working on porting the layers portion into tfa, asked owner for permission)
• Was it part of tf.contrib? (if so, where): no

Which API type would this fall under (layer, metric, optimizer, etc.)
layer

Who will benefit with this feature?
Developers who want to experiment with TCN layers.

Any other info.
Github issue that initialize the conversation to port TCN layers from @philipperemy's repo to tensorflow addons (see last two comments in this issue).
philipperemy/keras-tcn#73

[WindQAQ]

Good news! This is indeed in the scope of addons. Feel free to file a PR for it. Thanks!

[shun-lin]

@WindQAQ thanks! Will do so when I have time :)

[seanpmorgan]

TensorFlow Addons is transitioning to a minimal maintenance and release mode. New features will not be added to this repository. For more information, please see our public messaging on this decision:
TensorFlow Addons Wind Down

Please consider sending feature requests / contributions to other repositories in the TF community with a similar charters to TFA:
Keras
Keras-CV
Keras-NLP