* add -linear-schedule-with-warmup

* update lr scheduler usage in run_glue

* add import info

* add other 5 scheduler with warmup

* add copyright, update usage in run_glue

* simplify argument, make warmup arg support float and int

* Add some LambdaDecay scheduler with warmup, update usage in run_glue

* update classname and unify two cosine decays into one

* update usage in run_glue

* fix typo

* update WarmUp to Warmup, and update class name about Const, and update doc, and usage

* update usage of decay class

* update usage of decay class

* delete the images.

* delete the images.

* test

* test

* test

* test

* test

* test

* test

* test

* test

* test

* test

* test

* test

* test

* add imgs.

* The first version of plato2. Not finished the network.

* Update decode stratage.

* Update decode stratage.

* Completed the encoder and decoder. But it will oom.

* Completed the encoder and decoder.

* backend the code.

* Only completed the network of plato2 and nsp.

* Completed the development. But the effect has not be verified.

* Add readme and remove the code about deal PY2 and PY3.

* Modify comment.

* Modify readme and add images.

* Delete the data folder.

* Unified the task name with paddle1.8

* fixed bug.