* Add demo for combined strategies.

* Fix quan.

* Restore args in run.sh

* Shift up fluid models

* Update nlp submodules

* Add redirect guide in org readme

* Move HiNAS_models to AutoDL

* update acc curve
* fix test acc

* Move models to legacy, rename models_name to models, refine README
* Refine eval/infer/train code
* Release ResNet 18/34, GoogleNet and ShuffleNet v2.
* Add RMSProp optimizer.

1. Remove pretrain directory in data
2. Add download scripts into run.sh

Fix doc for human pose estimation and DeepLab v3+.

* remove KMP_BLOCKTIME setting

* remove duplicate

* update instruction

* fix bugs and remove redundant code
* minor changes and add README in Chinese

* add quant pass example.

* modify the step size for changing learning rate. test=develop

* use compiled binary to evaluate.

* mv quan pass example to the quant_low_level_api dir.

* Add some comments.

* fix some hyper parameters
* Update README

* Add demos for PaddleSlim on classification task.

* Refine structure of directory.

* add npairs loss
* fix metric learning readme

* deep interest network

* Added README for the ngraph engine

* Fix --model_save_dir

* Uncomment naive tests

* Update run.sh script

* update to use ngraph

* update readme

* Numactl -l was removed

* update instruction

* download pretrained model for inference only

* fix typo

* update

* fix shuffle gt bug.
* fix process exit bug.