Swish activation saves beta as weight even if it is not trainable

[aghoshpub]

- What I did Allows to save beta as weights when a model is saved even if beta is not trainable.

- How I did it Adding "trainable" argument to the weight.

- How you can verify it

---

This pull request fixes #482

[bot-of-gabrieldemarmiesse]

Hello, I'm a bot! I can make mistakes, notify gabrieldemarmiesse if I made one.

I see that you modified the following file:

• keras_contrib/layers/advanced_activations/swish.py

The owner of those file is @gabrieldemarmiesse

@gabrieldemarmiesse could you please take a look at it whenever you have the time and add a review? Thank you in advance for the help.

[gabrieldemarmiesse]

Closing because of the discussion in #482.