mirrors
/
mmyolo
mirror of https://github.com/open-mmlab/mmyolo.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
250 Commits
5 Branches
9 Tags
72 MiB
Commit Graph

250 Commits (89275adb290bffa89d8917cba01a85b3082fc514)
 

Author SHA1 Message Date
Seperendity 89275adb29
[CodeCamp] #50 Add module combination doc (#349) 
* the file  to verify the installation

* "add module_combination"

* add module_combination

* modified module_combination.md

* modify module_combination.md

* fix module_combination.md
 2023-01-06 20:30:48 +08:00
Jing Tang 7d07e1a780
Update yolo_detector.py (#441) 
将 YOLOX -> YOLO
 2023-01-06 19:20:24 +08:00
Nioolek 07afc3ee78
Fix potential bugs in rtmdet multi-scale training (#439) 
* Distinguish variables when training and testing

* beauty
 2023-01-06 19:03:14 +08:00
Haian Huang(深度眸) 884330108d
[BC Breaking] Keep the same input shape order as mmdet 3.0.0rc5 (#436) 
* Keep the same input shape order as mmdet

* add desc

* update

* update
 2023-01-06 19:00:30 +08:00
Nioolek 8127805dd3
[Feature] Support PPYOLOE training (#259) 
* 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: Range King <RangeKingHZ@gmail.com>

* Update tests/test_datasets/test_transforms/test_transforms.py

Co-authored-by: Range 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: Range King <RangeKingHZ@gmail.com>
Co-authored-by: hha <1286304229@qq.com>
Co-authored-by: huanghaian <huanghaian@sensetime.com>
 2023-01-06 15:54:39 +08:00
wzr-skn a20b160f0f
[CodeCamp]Add doc of yolov6_description.md (#382) 
* 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>
 2023-01-06 14:59:34 +08:00
MingJian.L c14ecc336c
[DOC] Update useful_tools.md (#384) 
* 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: HinGwenWoong <peterhuang0323@qq.com>

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
 2023-01-06 14:48:17 +08:00
tang576225574 2f399df2d6
[Feature] Add the unit test to test the `scale_factor` in LetterResize (#408) 
* 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: hha <1286304229@qq.com>
 2023-01-06 14:40:21 +08:00
Yijie Zheng 2290713ae6
[Fix] Fix bugs in the output annotation file when `--class-id-txt` is set. (#430) 
* [Fix] Fix bugs in the output annotation file when  is set.

* Update labelme2coco.py

* Update labelme2coco.py

* Improve code

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
 2023-01-06 11:41:17 +08:00
jason_w d8cbf216de
[Fix] Fix typo in docstring (#433) 
* fix typo in docstring

* fix typo in docs

* fix typo in docs
 2023-01-06 11:40:47 +08:00
RangiLyu 5172805dae
fix rtmdet-s cfg and neck (#434) 2023-01-06 11:40:19 +08:00
tripleMu 28439f102a
[Deploy] Support YOLOv7 easy deploy (#427) 
* Support YOLOv7 easy deploy

* Remove useless comment

* Fix mkdir
 2023-01-04 20:10:58 +08:00
tripleMu 7c5e21c39f
Fix customize dataset training (#428) 2023-01-04 20:02:02 +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
Xin Li c7a9026812
url fix in README (#426) 2023-01-03 15:43:23 +08:00
kitecats 14d9cab354
[CodeCamp] Add docs about how to freeze the weight of backbone or neck (#418) 
* Add docs about how to freeze the weight of backbone or neck

* refine the docs

* refine the docs

* refine the docs
 2022-12-31 16:36:40 +08:00
jason_w b1f7e80fe3
Fix typehint in Heads (#416) 2022-12-31 16:35:18 +08:00
jason_w 13de22dfd2
Fix typehint in YOLOv6 Head (#415) 2022-12-29 21:21:44 +08:00
RangiLyu cdc359c2de
fix batch inference bug (#413) 2022-12-29 17:18:54 +08:00
HinGwenWoong 99af3c980f
[Fix] Set metainfo fields to lower case and fix CI (#412) 
* Set metainfo fields to lower case

* Set metainfo fields to lower case

* Fix ci

* Fix ci
 2022-12-29 16:23:52 +08:00
tripleMu a44495868d
[Feature] Support PyTorch model forward for TensorRT inference (#377) 
* Support pytorch model forward for TensorRT

* Add ort wrapper

* Fix import

* Add deploy image-demo

* raise NotImplementedError

* Fix onnxruntime output gpu tensor
 2022-12-29 12:11:16 +08:00
tianlei 66c80e91e1
[Doc] update the English version of `custom_dataset.md` (#381) 
* part_1

* [WIP][Doc]update the part of 1. Prepare dataset

* update to 5. create a new config file

* update to 9.2 perform training

* add pre-commit

* 下一次更新内容

* update to 11.1.2 Creating a Docker container

* add pre-commit

* all updates complete!

* Update docs/en/user_guides/custom_dataset.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update docs/en/user_guides/custom_dataset.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update docs/en/user_guides/custom_dataset.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* modify en

* Update docs/en/user_guides/custom_dataset.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update docs/en/user_guides/custom_dataset.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* sync:Refactor dataset metainfo to lowercase

* Update docs/en/user_guides/custom_dataset.md

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

* Update docs/en/user_guides/custom_dataset.md

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

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
 2022-12-28 20:22:10 +08:00
kitecats d0a8aaa284
[CodeCamp] Add don't used pre-training weights to how_to (#404) 
* Add Don't used pre-training weights to how_to

* refine docs of how_to

* refine doc of how_to

Co-authored-by: Range King <RangeKingHZ@gmail.com>

* refine the doc

* refine the doc

Co-authored-by: Range King <RangeKingHZ@gmail.com>
 2022-12-28 17:00:29 +08:00
Nioolek 9ef883187a
[Feature] Show YOLOv5 assigner results (#383) 
* init commit

* init commit

* init commit

* 定稿，开始重构

* format code

* format code

* add typehint and doc

* init commit

* init commit

* init commit

* 定稿，开始重构

* format code

* format code

* add typehint and doc

* format code

* rollback

* add doc

* fix less img bug

* format code

* format code

* add README.md

* beauty

* beauty

* uniform name

* uniform name

* uniform name

* uniform name
 2022-12-28 16:40:14 +08:00
Range King bb4aea90da
[Refactor] Refactor dataset metainfo to lowercase (#362) 
* [Refactor] Refactor dataset metainfo to lowercase.

* Add docs

* Refactor metainfo to lowercase in new files

* Fix dataset meta compatibility
 2022-12-27 21:19:39 +08:00
tripleMu 81b7942de1
[Feature] Support `iscrowd` attribute training in YOLOv5 (#260) 
* [Feature] Support YOLOv7 inference (#149)

* update

* update

* update

* update

* update

* add docstr

* fix comments

* update

* [Feature] support mmyolo deployment (#79)

* support mmyolo deployment

* mv deploy place

* remove unused configs

* add deploy code

* fix new register

* fix comments

* fix dependent codebase register

* remove unused initialize

* refact deploy config

* credit return to triplemu

* Add yolov5 head rewrite

* refactor deploy

* refactor deploy

* Add yolov5 head rewrite

* fix configs

* refact config

* fix comment

* sync name after mmdeploy 1088

* fix mmyolo

* fix yapf

* fix deploy config

* try to fix flake8 importlib-metadata

* add mmyolo models ut

* add deploy uts

* add deploy uts

* fix trt dynamic error

* fix multi-batch for dynamic batch value

* fix mode

* fix lint

* sync model.py

* add ci for deploy test

* fix ci

* fix ci

* fix ci

* extract script to command for fixing CI

* fix cmake for CI

* sudo ln

* move ort position

* remove unused sdk compile

* cd mmdeploy

* simplify build

* add missing make

* change order

* add -v

* add setuptools

* get locate

* get locate

* upgrade torch

* change torchvision  version

* fix config

* fix ci

* fix ci

* fix lint

Co-authored-by: tripleMu <gpu@163.com>
Co-authored-by: RunningLeon <mnsheng@yeah.net>

* [Feature] Support YOLOv5 YOLOv6  YOLOX Deploy in mmdeploy (#199)

* Support YOLOv5 YOLOv6 YOLOX Deploy in mmdeploy

* Fix lint

* Rename _class to detector_type

* Add some common

* fix lint

Co-authored-by: huanghaian <huanghaian@sensetime.com>

* [DOC] Add deploy guide doc (#220)

* Add deploy doc-0

* Update 部署必备指南.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update 部署必备指南.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update 部署必备指南.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update 部署必备指南.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update 部署必备指南.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update 部署必备指南.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update 部署必备指南.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update 部署必备指南.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update 部署必备指南.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Del unused line

* Add docs

* Fix

* Fix

* Rename docs

* Rename docs

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* [Feautre] Add deploy dockerfile (#224)

* Add dockerfile for deploy

* Fix

* Update docker/Dockerfile_deployment

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update docker/Dockerfile_deployment

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Add opencv old version

* Add dockerfile and fix some typo

* Remove repeat packages

* Fix undefined symbol bug

* Update docker/Dockerfile_deployment

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

* Update docker/Dockerfile_deployment

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Add docs for deploy dockerfile

* Fix typo

* Update docs/zh_cn/advanced_guides/yolov5_deploy.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Add profiler

* Update docs/zh_cn/advanced_guides/yolov5_deploy.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update docker/Dockerfile_deployment

Co-authored-by: Range King <RangeKingHZ@gmail.com>

* Remove mmcv-full

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: Range King <RangeKingHZ@gmail.com>

* Add changelog of v0.1.2 (#226)

* Add changelog of v0.1.2

* update version

* fix comments

* fix comments

* update

* update version

* update version

* Support ignore

Cal loss with ignore

Typo

Fix import from mmdet

Fix train_cfg is None

* Fix judgement

* Fix bug and add a demo config

* Add new config

* remove

* rm

* remove loadanno

* Try 0

* Try-2

* fix

* add avg_factor

* update

* support rectangle training

* add ignore cfg

* update

* delete

* Fix

* Add unitest

* Add ignore_iof_thr

* Add test

Co-authored-by: Haian Huang(深度眸) <huanghaian@pjlab.org.cn>
Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com>
Co-authored-by: RunningLeon <mnsheng@yeah.net>
Co-authored-by: huanghaian <huanghaian@sensetime.com>
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: Range King <RangeKingHZ@gmail.com>
 2022-12-27 14:18:10 +08:00
caj-github 929b403fb0
Fix RuntimeError of `torch.cat()` expected a non-empty list of Tensors (#376) 
* RuntimeError: torch.cat(): expected a non-empty list of Tensors

* blank

* fix lint

* update

Co-authored-by: hha <1286304229@qq.com>
 2022-12-27 12:01:10 +08:00
zhubochao 6c5acd238c
Fix the device inconsistency error in yolov7 training (#397) 
* [FIX] Indices should be either on cpu or on the same device as the indexed tensor

* fix lint error

* use new_full instead of simple torch.ones

* fix lint error

* fix type error

* use existed tensor to create new_full tensor

Co-authored-by: zhubochao <zhubochao@zhubochaodeMacBook-Pro.local>
 2022-12-27 11:54:28 +08:00
tang576225574 46e7f6a477
[BUG] Fix the scale_factor and pad_param value in LetterResize (#387) 
* 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

Co-authored-by: hha <1286304229@qq.com>
 2022-12-27 11:45:23 +08:00
lvhan028 cccc792b94
remove 'context' argument from the rewriter function to 'YOLOv5Head.predict_by_feat' since mmdeploy has refactored it (#395) 2022-12-27 11:07:08 +08:00
Xin Li ab5665e840
update base v6 config name (#398) 2022-12-27 11:01:17 +08:00
Range King 25aa2a9cab
[Fix] Fix docstring graph rendering error of readthedocs (#400) 
* fix graph rendering of readthedocs

* Update base_yolo_neck.py
 2022-12-26 21:03:20 +08:00
Youfu b012154c10
CodeCamp #1519 [Docs] add yolox structure description (#402) 
* add yolox structure description

* Update configs/yolox/README.md

Co-authored-by: Range King <RangeKingHZ@gmail.com>

Co-authored-by: Range King <RangeKingHZ@gmail.com>
 2022-12-26 14:15:23 +08:00
Range King e00c3439f8
deprecating np.bool type alias (#396) 2022-12-21 10:11:13 +08:00
Yue WANG 王跃 1a0dfb0203
[Enhance]: Add resume from specific checkpoint in CLI (#393) 2022-12-20 10:25:19 +08:00
Range King ec367dba12
[Feature] Add a feature for the video demo (#392) 
* Create demo.mp4

* Create video_demo.py

* Update large_image_demo.py
 2022-12-19 19:49:41 +08:00
HinGwenWoong 446dfbd4b9
Add raise when class is blank or space between words (#391) 2022-12-19 16:55:33 +08:00
HinGwenWoong e0128c2dbd
[BUG] Fix YOLOv6 when get grid priors in `predict_by_feat` same shape will crash (#378) 
* [BUG] Fix with_stride

* [BUG] Fix with_stride

* [BUG] Fix with_stride

* [BUG] Fix with_stride

* [BUG] Fix with_stride

* A better to fix

* A better way

* A better way

* A better way

* A better way

* A better way

* A better way
 2022-12-19 14:40:04 +08:00
Range King d03dc0bfb5
[Docs] Add docs about how to set the random seed (#386) 
* how to set seed

* minor fix
 2022-12-19 14:17:44 +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
WANG Tengfei 2d5485f713
[CodeCamp] Add module_combination doc (#352) 
* [CodeCamp] Add module_combination doc
 * fix init_weights not match num_base_priors

 * add module_combination about yolov5 using other model loss

* Update module_combination.md

* [CodeCamp] Add module_combination doc
* update

* [CodeCamp] Add module_combination doc
 2022-12-17 10:37:53 +08:00
Zhaoyan Fang 14d6922b99
[CodeCamp] Add doc of yolov6_description.md (#372) 
* add assigner and loss description in yolov6_description.md

* Update docs/zh_cn/algorithm_descriptions/yolov6_description.md

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

* Update docs/zh_cn/algorithm_descriptions/yolov6_description.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update docs/zh_cn/algorithm_descriptions/yolov6_description.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update docs/zh_cn/algorithm_descriptions/yolov6_description.md

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

* Update docs/zh_cn/algorithm_descriptions/yolov6_description.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* update

* update

* update

Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
 2022-12-17 10:37:02 +08:00
Haian Huang(深度眸) 8cf8ab9ca3
[Feature] Add `crowdhuman` dataset (#368) 
* add crowdhuman dataset

* update

* update anhchor

* add pretrain link

* fix name

* remove batch_shapes_cfg

* add readme

* update readme

* update readme
 2022-12-15 16:37:09 +08:00
kitecats 70444f4d5c
[CodeCamp] Add doc of `module_combination` (#345) 
* [CodeMap]Add doc of module_combination

* refine doc

* refine doc

* update doc
 2022-12-15 13:00:08 +08:00
HinGwenWoong 00b138a184
[DOC] Add new video link for `custom dataset` (#365) 
* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link

* Add new video link
 2022-12-14 10:07:17 +08:00
q.yao d640e7b310
[Fix] Fix mmdeploy rewriter (#366) 
* fix mmdeploy rewriter

* fix unit test
 2022-12-14 09:59:32 +08:00
tianlei ac34b80e38
CodeCamp #58 [Doc] translate `rtmdet_description.md` of data aug part (#353) 
* CodeCamp #58 [Doc] translate rtmdet_description.md

* update the part of data augmentation

* update the part of 1.1.1

* add pre-commit

* Update docs/en/algorithm_descriptions/rtmdet_description.md

Co-authored-by: Range King <RangeKingHZ@gmail.com>

* Update docs/en/algorithm_descriptions/rtmdet_description.md

Co-authored-by: Range King <RangeKingHZ@gmail.com>

* Update docs/en/algorithm_descriptions/rtmdet_description.md

Co-authored-by: Range King <RangeKingHZ@gmail.com>

* Complete data augmentation

* Add torch1.13 checking in CI

* add pre-commit

Co-authored-by: Range King <RangeKingHZ@gmail.com>
 2022-12-13 15:10:01 +08:00
tripleMu 6fd50af6ab
Export onnx for model only (#361) 
* Support export onnx for model only

* Fix

* Fix
 2022-12-13 15:06:59 +08:00
tianlei e7ff6fcbf0
Add torch1.13 checking in CI (#363) 2022-12-12 15:49:54 +08:00
RunningLeon dcf73091e5
add mmyolo regression test yml (#359) 2022-12-12 10:27:21 +08:00