* Refine Image classification

This reverts commit 5e41760f.

* fix SENet154_vd name

* add densenet, squeezenet, darknet, resnext, resnext101_wsl pretrained models

* add mobilenet_v2_x0_5, resnext50_32x4d, resnext50_64x4d, xception41 pretrained models
* Update README_cn.md

* refine readme and fix train bug

* Including Fluid and Fluid-TensorRT inference time.

* Add readme and disable memopt

memopt may affect GC result

test=develop
Signed-off-by: Nzhaoyuchen <zhaoyuchen01@baidu.com>

* Disable memopt as GC opend

test=develop
Signed-off-by: Nzhaoyuchen <zhaoyuchen01@baidu.com>

* update image classification pretrained models

* update softmax

* Add mixup and distill and fix bugs

* recover test pyreader

* add error tip

* update README_CN

* fix distill bug

* add reader_cv2.py

* update run.sh

* fix docs

* fix typo

* polish train.py

* fix typo

* remove commented code

* fix typo

* fix_typo

* recover scale_loss

* fix typo

* fix bug

* fix test_program bug

Because WINDOWS does not support NCCL. It will raise an error when users try to run the multi-GPUs program on WINDOWS machine. So add a note to remind users to replace parallel executor to executor.

* Shift up fluid models

* Update nlp submodules

* Add redirect guide in org readme

* Move HiNAS_models to AutoDL

* 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.

* Delete file
* Rever the raw file

* Adjust the structure of whole repo

* Correct the readme for speec

* Update submodules LAC, Senta and SimNet

* Add python-cv2 reader for image classification.
* Update README_cn.md

* Add more model configure, such as AlexNet, VGG, GoogleNet, DPN, ResNet etc.
* Add download_imagenet2012.sh
* Update doc.
* Add Chinese doc.