transformer model based on Tensorlayer

[ArnoldLIULJ]

Checklist

• [x] I've tested that my changes are compatible with the latest version of Tensorflow.
• [x] I've read the Contribution Guidelines
• [x] I've updated the documentation if necessary.

Motivation and Context

Description

[ArnoldLIULJ]

Documentations haven't been done

[JingqingZ]

The dependency on Keras should be removed gradually.

tf.keras.optimizers -> tf.optimiziers tf.keras.initializers -> tl.initializers

[zsdonghao]

ready to merge?

[ArnoldLIULJ]

Add attention visualisation util Add attention visualisation test

[ArnoldLIULJ]

ready to merge?

not yet

[ArnoldLIULJ]

Add documentation Add attention-weights visualisation and pass unit-testing READY TO MERGE

[zsdonghao]

Hi, could you provide an example code in the examples folder? and update changelog.md ? thanks

[luomai]

There are some naming issues with this PR. Please don't merge it for now.

[luomai]

@ArnoldLIULJ any update?

[ArnoldLIULJ]

@ArnoldLIULJ any update?

was on vocation and would be working on a simplified tutorial today

[ArnoldLIULJ]

Add examples in example/translation_task/tutorial_transformer

[ArnoldLIULJ]

Hi, could you provide an example code in the examples folder? and update changelog.md ? thanks

done

[zsdonghao]

Hi the RST format is not correct in many function, please check~

[ArnoldLIULJ]

please check

[zsdonghao]

I think this one can be merged after the travis pass~.