* [FastDeploy] Add FastDeploy CPU/GPU deploy sources

* [FastDeploy] Add FastDeploy CPU/GPU deploy sources

* [FastDeploy] Add FastDeploy CPU/GPU deploy sources

* [FastDeploy] Add FastDeploy CPU/GPU deploy sources

* [FastDeploy] Add FastDeploy CPU/GPU deploy sources

* [Bug Fix] fixed python paddle_trt backend settings

* [Docs] Update ppdet docs for fastdeploy

* [Docs] fixed typos

* [Docs] Update ppdet-fastdeploy android docs

* Update fastdeploy pptinypose docs

* fixed cmake

* add SSOD_asrl

* modify traniner name

* add modelzoo

* add config

* add config

* add config

* modify cfg name

* modify cfg

* modify cfg

* modify checkpoint

* modify cfg

* add voc and lsj

* add voc and lsj

* del export

* modify

* modify

* refine codes

* fix fcos_head get_loss

* add export

* fix bug

* add export infer

* change

* retry

* fix eval infer

---------
Co-authored-by: Nnemonameless <nemonameless@qq.com>

* benchamrk set run 5m finish
* static train pop data['image_file']

* add ppyoloe_sod_qat

* ppyoloe sod qat

* add ppyoloe_sod qat demo

* fix ppyoloe sod qat yml

* add ppyoloe-sod ppyoloe_tiny qat

* add ppyoloe_sod_qat readme

* [TIPC] fix deformable_detr repeat

* [TIPC] fix dino batchsize

* [doc] add README for group detr

* add vitpose

* fix keypoints/README_en.md document_fix=test

* add vitpose_base_coco_256x192

* vitpose.py add some annotation for discriminate visio_transformer.py

* output_heatmap use gpu

align torch dn code

merge deformable dino mask-dino same code

reset norm attr

fix dino amp training

fix bbox_pred in detr postprocess

* refine swin configs and codes

* fix swin ppyoloe

* fix swin for ema and distill training

* fix configs for CI

* fix docs, test=document_fix

* fix ppyoloe_distill and docs

* fix docs, test=document_fix

* [TIPC] fcos add static train

* tinypose_128x96 add training static

* [TIPC] tinypose add static training

* disable maskrcnn static training

* add raw codes

* add pretrained weights

* fix reader

* fix

* fix focalnet codes coments and format

* fix focalnet codes coments and format

* fix focalnet format

* metro con reverse

tinypose3d fix

readme modelzoo

* fix tinypose3d

* new adapted

* test ok

* fix run_benchmark for small model accurate speed

* fix run_benchmark for other det models

* add config and architecture for human36m

* modify TinyPose3DHRNet to support human3.6M dataset

* delete useless class

* petr train ok

train ok

refix augsize

affine size fix

update msdeformable

fix flip/affine

fix clip

add resize area

add distortion

debug mode

fix pos_inds

update edge joints

update word mistake

* delete extra codes;adapt transformer modify;update code format

* reverse old transformer modify

* integrate datasets