* add gru and bigru net

* add gru and bigru

* add gru and bigru

* update .run_ce.sh

* chmod +x .run_ce.sh

* add ce

* add ce

* add ce

* add ce

* add ce for xlnet

* add ce for xlnet

* add xlnet ce

* add max_iters and profiler for detection models

* update for detection models

* add profiler and max_iter for yolov3 model

* modify image_classification train

* update train.py

* modify args position

* Create DANet

* reset auc more elegant and fix bug and README in ctr/dnn

* change ctr/dnn README

* fix apis, including os.path, shell and multiprocess

* use mul.cpu_count in win

* PaddleRec release 1.6 api update

* Update README.md

* Update README.md

bold remind of paddle version

* Update README.md

change paddle version note

* add PaddleKG/CoKE

* modify README.md to add CoKE arxiv link and citation

* fix language_model enable to run multi GPUs tasks

* fix a bug of save model

* fix a bug of save model

1. Fix format of arguments
2. How to get model size
3. Add FAQ for compress other model

This is lbam model for picture inpainting

* add line space in PaddleVideo README

* add authors information for ets and tall

* fix shufflenet v2 bug

* Add project transfer info in README
* Update link in models/README.md for detection model