* keypoint petr (#7774)

* 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

* add config and architecture for human36m (#7802)

* add config and architecture for human36m

* modify TinyPose3DHRNet to support human3.6M dataset

* delete useless class

---------
Co-authored-by: XYZ <1290573099@qq.com>

* fix distill codes and docs

* fix slim distill docs

* fix docs

* add details of docs, test=document_fix

* update pphuman ppvechicle new models, test=document_fixb

* update docs, test=document_fixb

* update docs, test=document_fix

* fix configs, test=document_fix

* GradCAM Refinement

* ROI CAM bugfix

* Add support for blazeface, ssd, retinanet

* Change nms return_idx default value to False

* Add use_extra_data attr

* pre-commit code style

* fix yolo extra_data process

* add mainkd for ppyoloe distill

* refine code style

* add ppyoloe semi-det base codes

* fix configs

* fix head distill loss

* add more semi_det configs and fix doc, test=document_fix

* add contrast_loss config, test=document_fix

* add QueryInst

* update sparse config

* Clean up redundancy and update style

* update config

* add trained models & resolve conflict

* share bbox_cxcywh_to_xyxy

* Revert "share bbox_cxcywh_to_xyxy"

This reverts commit ccf811211eda0a59dc0446f1b716f4e7412367f9.

* repeat bbox_cxcywh_to_xyxy

* Poly2Mask: Add delete switch
RandomSizeCrop: keep origin randint style

* update copyright

* add ppyoloe distill with soft loss and feature loss

* refine distill codes

* fix configs and docs

* clean codes

* merge cam, fix export

* fix slice infer one image save_results (#7654)

* Support GradCAM Cascade_rcnn forward bugfix

* code style fix

* BBoxCAM class name fix

* Add gradcam tutorial and demo

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

* add ppyoloe plus tiny with aux_head

* fix ppyoloe tiny training

* fix ppyoloe+ tiny p2 model

* add ppyoloe t p2 model

* add centertrack base codes

* fix deploy and docs

* fix tracker

* fix

* fix pre_img

* fix deploy

* fix

* add DINO

add msdeformable attention cuda op

fix export bug

* fix decoder norm

* finish_cotuning

* fix_bug

* add_readme

* finish contrast

* fix transposed convolution in_channels

* fix when deep_supervision is false

* add ssod denseteacher fcos codes and refine baseline doc

* fix docs

* fix deploy and ColorJitter float32

* fix docs

* fix docs, test=document_fix

* add iou-fcos and ssod baseline

* add gen_semi_coco, fix doc

* fix doc links

* fix sm_use for ppyoloe_head and output for box_dis

* fix pos_embed of training

* [smdet] add tal_cr and custompan with transfomer, add box_distribution to pred reg_max, test=document_fix

* add tal_cr

* add ppyoloe_r

* modify code of ops.py

* add ppyoloe_r docs and modify rotate docs

* modify docs and refine connfigs

* fix some problems

* refine docs, add nms_rotated ext_op and fix some problems

* add image and inference_benchmark.py

* modify docs

* fix some problems

* modify code accroding to review

Co-authored-by: wangxinxin08 <>

* add code

* add ld-vlr

* refractor code

* refine code

* add doc

* refine details

* refine doc

* update download url

* rename config file for ci

* rename config file in README for CI

* refine fcos codes

* refine fcos postprocess

* fix fcos deploy

* fix fcos deploy

* add fcosr

* fix some problem

* add docs for fcosr

* modify code

* modify focsr reader

* finish tensorrt deployment with dynamic shape

* modify according to review comment

Co-authored-by: wangxinxin08 <>

* compat dev & release

* fix ops import