Skip to content

M
mmyolo

u013913216 / mmyolo
与 Fork 源项目一致

从无法访问的项目Fork

通知 1
Star 0
Fork 0
M
mmyolo

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

切换分支/标签
  1. 18 1月, 2023 8 次提交
  3. 17 1月, 2023 2 次提交
  5. 16 1月, 2023 1 次提交
  7. 12 1月, 2023 3 次提交
  9. 11 1月, 2023 3 次提交
    • H
      [Feature] Support YOLOv8 inference (#445) · 935d710f
      由 HinGwenWoong 提交于 
      * Add backbone

* Improve code

* fix

* Add neck

* Add config

* Fix layer param

* Fix layer param

* Add head

* Add head

* Add model converter

* Add model converter

* Add model converter

* Improve code

* update

* update

* align test

* Improve code

* Improve code

* Improve code

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Improve code

* Improve code

* Improve code

* Add configs

* Improve doc

* Improve doc

* update

* Fix config

* update

* Fix config

* Fix config

* update

* Fix config epoch

* update

* Fix docstr

* Add UT

* Add UT

* Fix doc

* update

* Fix lint

* Fix doc

* Fix config name

* Improve config

* Improve default

* Add docstr

* Improve code

* Improve code

* Drop `bbox_head.head_module.dfl.conv.weight` when convert to mmyolo weight

* Delete useless code

* Add batch_shapes_cfg but not enable it.

* update
Co-authored-by: Nhuanghaian <huanghaian@sensetime.com>
      935d710f
    • T
      [Feature] Add new YOLOX bbox coder for TensorRT-8 and fix TensorRT-7 bug (#450) · f1855ca6
      由 tripleMu 提交于 
      * Add yolox bbox decoder for tensorrt backend

* Fix tensorrt7+ bug
      f1855ca6
    • Y
      [Fix] Fix import error in `optimize_anchors.py` (#452) · fd0f07b8
      由 Yijie Zheng 提交于 
      * [Fix] Fix bugs in the output annotation file when  is set.

* Update labelme2coco.py

* Update labelme2coco.py

* Improve code

* [Fix]Fix import error in optimize_anchors.py

* [Fix]Fix import error in optimize_anchors.py
Co-authored-by: NHinGwenWoong <peterhuang0323@qq.com>
      fd0f07b8
  11. 09 1月, 2023 1 次提交
  13. 08 1月, 2023 3 次提交
  15. 07 1月, 2023 1 次提交
  17. 06 1月, 2023 11 次提交
    • S
      [CodeCamp] #50 Add module combination doc (#349) · 89275adb
      由 Seperendity 提交于 
      * the file  to verify the installation

* "add module_combination"

* add module_combination

* modified module_combination.md

* modify module_combination.md

* fix module_combination.md
      89275adb
    • vaew's avatar
      Update yolo_detector.py (#441) · 7d07e1a7
      由 vaew 提交于 
      将 YOLOX -> YOLO
      7d07e1a7
    • N
      Fix potential bugs in rtmdet multi-scale training (#439) · 07afc3ee
      由 Nioolek 提交于 
      * Distinguish variables when training and testing

* beauty
      07afc3ee
    • 深度眸's avatar
      [BC Breaking] Keep the same input shape order as mmdet 3.0.0rc5 (#436) · 88433010
      由 深度眸 提交于 
      * Keep the same input shape order as mmdet

* add desc

* update

* update
      88433010
    • N
      [Feature] Support PPYOLOE training (#259) · 8127805d
      由 Nioolek 提交于 
      * add ppyoloe backbone, neck

* add ppyoloe test

* add docstring

* add ppyoloe m/l/x configfile

* add ppyoloe_coco.py

* rename config

* add typehint

* format code; add ut

* add datapre

* add datapre

* add ppyoloe datapre

* add ppyoloe datapre

* add ppyoloe datapre

* reproduce coco v0.1

* add ut

* add ut, docstring

* fix transforms bug

* use mmdet dfloss

* add non plus model config

* add non plus model config

* fix

* add ut

* produce coco v0.2

* fix config

* fix config

* fix eps and transforms bug

* add ema

* fix resize

* fix transforms.py

* fix transforms.py

* fix transforms.py

* old version

* old version

* old version

* old version

* old version

* old version

* fix stride loss error

* add INTER_LANCZOS4

* fix crop bug

* init commit

* format code

* format code

* bgr transforms.py

* add typehint and doc in transforms.py

* 继承新版yolov6head写法，删除不必要的注释

* fix transforms var name bug

* bbox decode use stridetensor insted of priors

* add headmodule todo

* add ppyoloe README.md

* add ppyoloe README.md

* Update tests/test_datasets/test_transforms/test_transforms.py
Co-authored-by: NRange King <RangeKingHZ@gmail.com>

* Update tests/test_datasets/test_transforms/test_transforms.py
Co-authored-by: NRange King <RangeKingHZ@gmail.com>

* save ckpt last 10 epochs

* save_best ckpt

* del ppyoloe collate

* change name of ppyoloebatchrandomresize

* add the reason for rewritten PPYOLOEDetDataPreprocessor

* solve ppyoloerandomresize name error

* rm PPYOLOERandomExpand

* rm l1 loss

* rm yolov6 loss_obj

* add difference between yolov6 and ppyoloe

* add reason for rewrite paramscheduler

* change proj init way

* fix error

* rm proj_conv in pth

* format code

* add load_from

* update

* support fast training

* add pretrained model url

* update

* add pretrained model url

* fix error

* add imagenet model convert and use init_cfg to init backbone

* add plus model pretrain model

* add ut

* add ut

* fix ut

* fix withstride bug

* cat in yolov5_collate

* merge

* fix typehint

* update readme

* add reason for gap

* fix log in README.md

* rollback yolov6

* change inherit

* fix ut

* fix ut
Co-authored-by: NRange King <RangeKingHZ@gmail.com>
Co-authored-by: 深度眸's avatarhha <1286304229@qq.com>
Co-authored-by: Nhuanghaian <huanghaian@sensetime.com>
      8127805d
    • W
      [CodeCamp]Add doc of yolov6_description.md (#382) · a20b160f
      由 wzr-skn 提交于 
      * YOLOv6网络结构文档

* 修正YOLOv6网络结构文档

* 修改模型结构图四周多余的留白

Co-authored-by: yl4203 <wsnbbzwd19960817>
      a20b160f
    • M
      [DOC] Update useful_tools.md (#384) · c14ecc33
      由 MingJian.L 提交于 
      * Update useful_tools.md

更新了浏览数据部分的文档

* Update useful_tools.md

* Update useful_tools.md

* Update useful_tools.md

* Update docs/zh_cn/user_guides/useful_tools.md
Co-authored-by: NHinGwenWoong <peterhuang0323@qq.com>
Co-authored-by: NHinGwenWoong <peterhuang0323@qq.com>
      c14ecc33
    • tang576225574's avatar
      [Feature] Add the unit test to test the `scale_factor` in LetterResize (#408) · 2f399df2
      由 tang576225574 提交于 
      * correct the scale_factor and pad_param value in LetterResize

* correct the scale_factor and pad_param value in LetterResize

* correct the scale_factor and pad_param value in LetterResize

* tang

* update

* tang

* tang

* fix linting

* tang

* tang

* tang
Co-authored-by: 深度眸's avatarhha <1286304229@qq.com>
      2f399df2
    • Y
      [Fix] Fix bugs in the output annotation file when `--class-id-txt` is set. (#430) · 2290713a
      由 Yijie Zheng 提交于 
      * [Fix] Fix bugs in the output annotation file when  is set.

* Update labelme2coco.py

* Update labelme2coco.py

* Improve code
Co-authored-by: NHinGwenWoong <peterhuang0323@qq.com>
      2290713a
    • J
      [Fix] Fix typo in docstring (#433) · d8cbf216
      由 jason_w 提交于 
      * fix typo in docstring

* fix typo in docs

* fix typo in docs
      d8cbf216
    • R
      fix rtmdet-s cfg and neck (#434) · 5172805d
      由 RangiLyu 提交于
      5172805d
  19. 04 1月, 2023 3 次提交
  21. 03 1月, 2023 1 次提交
  23. 31 12月, 2022 2 次提交
  25. 29 12月, 2022 1 次提交