* Disable optimizer fusion for RCNN models

waiting for upstream fix

* Disable completely

* Add support for mixed precision training

* Disable `fuse_all_reduce_ops` when training in mixed precision

waiting for upstream fix

* Initial support for distributed training

* Housekeep on rank 0 only

* Conform to models convention

* update TensorRT 1.5.2 inference time

* add EfficientNet configuration in README

* add notes for the ported weight of EfficientNet

* fix_infer_pix2pixreader

Add EfficientNet

* fix rcnn eval on voc

* update comment

* add SPADE

* fix mobilenet bug

* fix inplce warning

* refine auto download logs

* add BSN and BMN models to PaddleVideo

* modify codes to fix metrics evaluation and readme

* add copyright for gen_infer_list.py and modify the content of README

* add BSN and BMN in models/README.md

refine image classification and add 19 pre-trained models.

Add PaddleSeg submodule to PaddleCV

In PaddleDetection,  making use of tb-paddle to record data, so as to display in TensorBoard.  (#3295)

* use tb_paddle to log data
including:

* loss
* mAP
* image

* modified:   requirements.txt
* modify the missing argument --use_tb
* modify GETTING_STARTED.md and docs/GETTING_STARTED_cn.md

add the argument of tb-paddle in docs.
* optimize the display name of image displaying.

* remove use_inplace=True and add save_step params

* remove useless params when using global pooling

fix lsr bug in image classification

* Refine Image classification

* Add benchmark (fps) in MODEL_ZOO doc