Kashgari

* Add BERT output feature layer finetune support. Discussion: 103
* Add BERT output feature layer number selection, default 4 according to BERT paper.
* Fix BERT embedding token index offset issue 104.

* fix missing `sequence_labeling_tokenize_add_bos_eos` consig

* multi-label classification for all classification models
* support cuDNN cell for sequence labeling
* add option for output `BOS` and `EOS` in sequence labeling result, fix 31

* add `AVCNNModel`, `KMaxCNNModel`, `RCNNModel`, `AVRNNModel`, `DropoutBGRUModel`, `DropoutAVRNNModel` model to classification task.
* fix several small bugs

* fix BERT Embedding model's `to_json` function, issue 19

* remove class candidates filter to fix 16
* overwrite init function in CustomEmbedding
* add parameter check to custom_embedding layer
* add `keras-bert` version to setup.py file