Commit Graph

12 Commits (dev)

Author SHA1 Message Date
Youfu 2813e89f44
[Feature] Implement fast version of YOLOX (#518)
* Implement fast version of YOLOX

* config change

* Update yolox_head.py

* Update mmyolo/models/data_preprocessors/data_preprocessor.py

Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>

* Update mmyolo/models/data_preprocessors/data_preprocessor.py

Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>

* add test and modify faults

* fix lint

* fix lint

* modify metafile and README

* modify metafile and readme

* fix

* fix

* fix

* fix

* fix

* fix test

---------

Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
2023-02-08 20:10:03 +08:00
Nioolek 07ab35222c
[Feature] Support YOLOv8 training (#458)
* add v8 training head

* add training config

* update

* update1

* update all config

* update all config

* update metafile

* add head loss

* update readme

* iou2ciou in tal, add config

* change init layer

* update

* update

* add clip_grad

* update max_aspect_ratio

* add init

* fix aug config

* update forward

* add official v8 loss

* add official v8 loss

* 同步预测方式

* fix loss bug

* delete useless code

* 替换iou,但还有问题

* fix bug

* fix empty

* add UT

* add UT

* update readme

* replace iou_cal

* add use_ciou docstr

* update metafile

* update metafile

* update metafile

Co-authored-by: huanghaian <huanghaian@sensetime.com>
Co-authored-by: hha <1286304229@qq.com>
2023-01-18 14:16:37 +08:00
RangiLyu 48f8896e84
[Feature] Implement fast version of RTMDet. (#425)
* Accelerate RTMDet

* update

* update

* update

* update1

* update2

* update pipeline

* update lr cudnnbenchmark

* revert batchsize

* fix batch inference

* refactor head

* update box

* bs=16

* update

* move reduce mean

* update head

* per img loss

* fix

* fix sum

* concat loss

* batch dsla

* sort topk

* bs 32

* clean code

* update readme

* update ut

* update checkpoint

* num_class

* clean code

* resolve comments

* fix readme

* fix ut

Co-authored-by: huanghaian <huanghaian@sensetime.com>
Co-authored-by: hha <1286304229@qq.com>
2023-01-04 16:06:44 +08:00
Range King 051d30a41a
[Fix] Fix CI error due to `np.int` and legacy builder.py (#389)
* Update utils.py

* fix docs

* Remove legacy build_detector

* Update test.yml

* fix error
2022-12-19 14:15:58 +08:00
Haian Huang(深度眸) 573ff033e4
[Feature] Support YOLOv7 P5 training (#243)
* support yolov7

* update dev

* update headmodule and convert

* update

* fix pipeline

* fix loss

* fix optimizer parameter groups

* refactor mosaic9

* refactor optim

* refactor loss

* refactor

* refactor

* refactor new

* support yolov7x

* refine

* support tiny

* refactor model

* refactor model

* support yolov7x inference

* support yolov7-tiny inference

* support yolov7-e inference

* refactor

* support yolov7-tiny train

* add docstr

* fix merge error

* fix merge error

* fix merge error

* fix lint

* fix lint

* fix lint

* fix UT

* update

* update
2022-11-21 17:30:19 +08:00
wanghonglie 980e908618 [Feature] Support YOLOv6 training (#183)
* init v6 loss

* init v6s train

* Add train pipeline

* Add lr scheduler

* update

* update

* update

* update

* update

* update

* update

* update

* update

* fix detach bug

* fix detach bug

* update

* Add stop aug hook

* Add save best ckpt

* update

* Add PipelineSwitchHook

* Fix train pipeline stage 2

* update

* Fix train pipeline

* update

* fix stage2 randomaffine bug

update

update

clean

clean

* update letterResize param

* add v6affine config

* add v6 randomaffine

* update v6 config

* update

* update

* update

* update

* update config param

* update

* update

* refactor iou loss % rm v6affine

* update

* rm dfl

* add v6 300 epoch config

* Factor batch atss assigner

* Format code

* Format code

* Roll back

* Refactor dist_calculator

* Refactor select_candidates_in_gts

* Refactor select_highest_overlaps

* Refactor iou_calculator

* Refactor all code

* Improve docstr

* Improve code

* clean config

* add nano tiny config

* pre-commit

* Refactor

* Improve code

* Improve naming and link

* Add UT

* pre commit

* Add UT

* Add UT

* Improve code, using mmdet.BboxOverlaps2D for all iou calculation

* Improve code, using mmdet.BboxOverlaps2D for all iou calculation

* Improve code

* pre commit

* pre commit

* Add UT

* fix config

* pre commit

* Improve code

* Improve code

* Improve code

* Improve code

* [Refactor] YOLOv6 BatchATSSAssigner (#179)

* Factor batch atss assigner

* Format code

* Format code

* Roll back

* Refactor dist_calculator

* Refactor select_candidates_in_gts

* Refactor select_highest_overlaps

* Refactor iou_calculator

* Refactor all code

* Improve docstr

* Improve code

* Improve code

* Improve naming and link

* Add UT

* pre commit

* Add UT

* Add UT

* Improve code, using mmdet.BboxOverlaps2D for all iou calculation

* Improve code, using mmdet.BboxOverlaps2D for all iou calculation

* Improve code

* pre commit

* Fix conflicts

* Improve code

* Improve code

* Improve code

* Improve code

* Improve code

* Improve code

* add utils.py, order the input param

* Improve docstr

* Fix lint

* Improve param mapping

* Improve param mapping

* Improve naming

* assigner return dict

* update

* update config

* update config

* Fix

* Fix UT

* Improve UT

* Improve naming

* Improve coding

* pre commit

* pre commit

* pre commit

* Fix ci

* Improve naming

* Improve coding

* Fix training iou calculate error

* Improve naming

* Improve naming

* Improve type hint

* fix lint

* fix conflicts

* fix UT

* Improve type hint

* Improve naming

* Improve coding

* Improve coding

* Fix UT

* Refactor SIoU

* Pre commit

* Fix

* Improve ciou

* Improve ciou

* refactor varifocal

* Improve ciou

* Improve ciou

* Improve siou

* Improve type hint

* Improve siou

* Improve siou

* Fix lint

* refactor varifocal

* fix iou bug

* fix siou and loss_cls bug

* update

* update

* add scope

* update

* update

* Improve func `gt_instances_preprocess`

* support deploy mode

* Improve func `gt_instances_preprocess`

* Improve func `gt_instances_preprocess`

* Improve func `gt_instances_preprocess`

* Improve func `bbox_overlaps`

* Improve coding

* Improve bbox_overlaps

* Delete useless code

* add yolov6 deploy mode hook

* fix lint

* Add common attributes to reduce calculation

* Improve code

* Improve code

* Fix bug

* Fix bug

* update

* add readme

* update readme

* update readme url

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
2022-11-03 19:03:06 +08:00
Haian Huang(深度眸) bb3aa48689 [Feature] Support RTMDet (#85)
* add cspnext

* add neck


* update

* align s,tiny test

* update

* update

* fix bug of UT

* fix typehint

* fix resize bug

* update s and tiny

* update s and tiny link

* update convert

* add cls config with rtmdet

* update config


* fix ci error

Co-authored-by: wanghonglie <wanghonglie@pjlab.org.cn>
2022-09-29 19:09:56 +08:00
huanghaian c26a12ed32 Add docstring 2022-09-21 15:09:47 +08:00
huanghaian 66dcc4d3d2 fix import order 2022-09-20 10:57:33 +08:00
hha cc6ac864c9 update featmap_vis_demo and format code 2022-09-18 17:04:14 +08:00
HinGwenWoong 1915c04e5d
[Fix] Improve type hint (#22)
* Fix type hint

* Delete `-> None` when no return val

* format code
2022-09-18 17:02:00 +08:00
hha cfec074cf6 init commit 2022-09-18 10:11:55 +08:00