* Update PaddleDetection/README_cn.md
* Follow comments
* Small update

* Add inference benchmark
* Adjustment order
* Update some descriptions

* refine doc for transfer learning

* add face doc
* update face detection readme and add demo jpg

* refine download sh to py

* update QUICK_STARTED

* Error out if fp16 is enabled and affine channel is used

* Add more documentation on mixed precision training

* Document mixed precision training flags

* Clarify GPU is required for mixed precision training

* Support finetune by custom dataset

* add finetune args

* add load finetune

* reconstruct load

* add transfer learning doc

* add fruit demo

* add quick start

* add data preprocessing FAQ

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.

* Add benchmark (fps) in MODEL_ZOO doc

* add gn doc

* update model zoo doc

* add yolov3_darknet cinfig comment

* fix commment

* add log_iter

* Add full configs example & refine doc

* refine docs

* add_ssd_config_demo

* Add cascade deformable mdoels
* Fix MODLE_ZOO.md

# Add VGG-SSD on VOC and COCO dataset.
# Add config and model zoo. 
# Refine bbox2out and draw_bbox:
    - Add bbox de-normalize in bbox2out function.
    - Remove bbox de-normalize in draw_bbox.

* update doc in PaddleDetection

* add save best model & fix dcn configs

* add deformable models
* fix dcn v2
* fix log_iter

* fix cn docs

* fix easy problem

* update GETTING_STARTED.md

Add PaddleDetection docs & some model configs

* add voc_eval and yolo_darknet_voc

* add yolov3_darknet_voc in MODEL_ZOO

* fix default im_size

* fix MODEL_ZOO note

* fix is_bbox_normalized

* extract map to map_utils.py

* update yolov3_dorknet_voc mixup

* add yolov3_r34_voc

* add yolov3_mobilenet_v1_voc

* fix drop empty in VAL mode

* use cfg.num_classes

* assert metric valid

* enable difficulty can be None

* add comment for bbox_eval

* num_classes in retinanet

* Fix ResizeImage and data transform for SSD
* Fix code style

* fix infer doc and config default

* refine dataset exists

* fix None proc

* fix resnet for resnet34

* fix ResNet18 and ResNet34

* update modelzoo and fix configs

* fix configs

* fix resnet bn