add xDeepFM, DCN model in PaddleRec/ctr.
change DeepFM data download script.

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

* Release auto mixed-precision training for bert

* Update README

* modify readme for not support windows cpu environment

* modify readme for python adaption

fix lsr bug in image classification

* add readme for KTNET

* update readme

* update readme

* update readme

* update readme of KTNET

* update readme of KTNET

* add source files for KTNET

* update files for KTNET

* update files for KTNET

* update draft of readme for KTNET

* modified scripts for KTNET

* fix typos in readme.md for KTNET

* update scripts for KTNET

* update scripts for KTNET

* update readme for KTNET

* edit two-staged training scripts for KTNET

* add details in the readme of KTNET

* fix typos in the readme of KTNET

* added eval scripts for KTNET

* rename folders for KTNET

* add copyright in the code and add links in readme for KTNET

* add the remaining download link for KTNET

* add md5sum for KTNET

* final version for KTNET

* Refine Image classification

remove mem opt in PaddleNLP

* Add benchmark (fps) in MODEL_ZOO doc

* fix add map_type

* Refine arguments of ocr models.

* Add comments for issue of attention model in paddle1.5

* fix used

This reverts commit 5e41760f.

* update .run_ce.sh

* chmod +x .run_ce.sh

* add elmo ce

* minor fix for PaddleDetection

* fix SENet154_vd name

* fix bug in sharedmemory
* fix bug in sharedmemory

* fix reader, metrics, frameworks to increase universality of PaddleVideo

* change config files from .txt to .yaml

* fix input to use PyReader and modify on readme to fit new codes

* adjust code structure and modify configs and readme to fit standard

* modify links of pdparams in readme and scripts

* fix pickle.dump in python3 and modify on readme of attention_lstm

* add description of weights argument in eval/predict/inference_model.py

* add cascade gn

* add cascade mask gn config

* update configs