* Update README.md (#4267)

* test=develop (#4269)

* 3d use new api (#4275)

* PointNet++ and PointRCNN use new API

* Update Readme of Dygraph BERT (#4277)

Fix some typos.

* Update run_classifier_multi_gpu.sh (#4279)

remove the CUDA_VISIBLE_DEVICES

* Update README.md (#4280)

* 17 update api (#4294)

* update1.7 save/load & fluid.data

* update datafeed to dataloader

* Update resnet_acnet.py (#4297)

Bias attr of square conv should be "False" rather than None during training mode.

* move danet to Paddle/Contrib (#4285)

* update new api for rrpn (#4296)

update new api for rrpn

* Fix transformer save_inference_model (#4306)

* upgrade save and load interface (#4311)

* upgrade dcn and xdeepfm, change from all old save/load api to fluid.save and fluid.load
* test=develop

* modify save and load to 1.7 api for rrpn (#4310)

* modify save and load to 1.7 api

* add func to load parm

* Add VOT models (#4257)

* First version for VOT models.
* Include SiamFC and ATOM.
* A unified architecture for ATOM and Siames series models.

* update vot code (#4338)

* [VOT]Remove local.py generate step, add tracking gif to README (#4344)

* update vot code
* remove local.py generate step, add tracking gif to README
* fix word usage in readme
* add got10k download website
* add pip install paddlepaddle-gpu
* fix word usage

* do not print stack frame when train process killed (#4346)

* do not print stack frame when train process killed
* add note about VOT does not support windows platform!

* test=develop add word2vec demo
Co-authored-by: NKaipeng Deng <dengkaipeng@baidu.com>
Co-authored-by: Nzhang wenhui <frankwhzhang@126.com>
Co-authored-by: Nparap1uie-s <parap1uie-s@users.noreply.github.com>
Co-authored-by: Nwangguanzhong <jerrywgz@126.com>
Co-authored-by: Nchengjuntao <18222160892@163.com>
Co-authored-by: Nliu zhengxi <380185688@qq.com>
Co-authored-by: Nxujiaqi01 <173596896@qq.com>
Co-authored-by: NDouble_V <liuvv0203@163.com>

* add rrpn for models

* refine doc for transfer learning

Update ppdet/utils/checkpoint.py to skip the var shape check when the var is not initialized. (#3452)

* 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

* Initial support for distributed training

* Housekeep on rank 0 only

* Conform to models convention

Add PaddleDetection docs & some model configs

* Rename object_detection to PaddleDetection
* Small fix for doc

* Unified object detection framework based on PaddlePaddle.
* Include algo: Faster, Mask, FPN, Cascade, RetinaNet, Yolo v3, SSD.