v0.8.3

- add DCN-M(DCN V2) and DCN-Mix model
- add transform_fn for DenseFeat
- simplify  methods in `interaction.py`
- change output shape of  BilinearInteraction used in  FiBiNET
- update docs and test files

v0.8.2

Refactor DNN Layer

v0.8.1 release (shenweichen#276)

- Improve the reproducibility 
- Fix some bugs

v 0.8.0

- Support `Tensorflow Estimator` for large scale data and distributed training.  
- Support  different initializers for different embedding weights by settting `embeddings_initializer` of `SparseFeat`
- Support using pretrained weights to initialize embedding weights and frozen embedding weights. 
- Add new model `FwFM`
- API changes

v 0.7.5

- Fix numerical instability in `LayerNormalization`
- update `PNN` api

add flen

Add FLEN: Leveraging Field for Scalable CTR Prediction

Fix the inconsistency of prediction results when the model is loaded …

…with trained weights

fix some bugs (shenweichen#185)

- fix bug in `get_varlen_pooling_list`
- fix bug in `SequencePoolingLayer` when `mode='max'`
- Add alias `ONN` for model `NFFM`

v0.7.1

* Simplify `VarLenSparseFeat`, support setting weight_normalization.

* Fix problem of embedding size of `SparseFeat` in `linear_feature_columns`.

refactor feature columns

refactor feature columns 
- different features can use different `embedding_dim`
-  group-wise interaction is available by setting `group_name`