bf6d9e9451
Fix RTMDet visualization to new code ( #550 )
...
* fix bug to newer code
* adjust picture format
* add offset for rtmdet
* rewrite axis to fix format
* easier way to get axis
2023-02-14 09:45:38 +08:00
8d2a7d1ab2
Update rtmdet_tiny_ofa_lat31_syncbn_16xb16-300e_coco.py ( #551 )
2023-02-13 19:42:49 +08:00
75618020f8
RTMDet Assigner visualization ( #528 )
...
* fix format
* return multiple pos assigns
* rewrite to get matched_gt_inds
* ignore corrupted images
* rm RTMDetectorAssigner
* fix bug for different devices
* add warnings when use rtmdet without checkpoint
* add priors for rtmdet
* fix format
* add readme
* fix format
* fix readme and typo
* typo
* fix note
2023-02-13 11:42:11 +08:00
164c319493
[Feature] Support MMRazor searchable backbone ( #453 )
...
* update subnet cfg
* add docs
* update model link
* fix lint
* mdformat
* update readme
* fix lint
* update link
* rename folder
* fix readme
* update readme
* make lint
* rename
* update readme
* sync mmrazor cfg
* fix cfg
* install issue
* require mmcls
* fix yolo cfg
---------
Co-authored-by: aptsunny <aptsunny@tongji.edu.cn>
Co-authored-by: sunyue1 <sunyue1@sensetime.com>
2023-02-10 16:24:47 +08:00
3a6899e232
[Improve] Beautify the YOLOX configuration ( #529 )
...
* Beautify the YOLOX configuration
* fix checks
* Update configs/yolox/yolox_s_fast_8xb8-300e_coco.py
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
* fix letter case problem
* beauty yolox configs except yolox_s's config
* fix lint
* Update configs/yolox/yolox_s_fast_8xb8-300e_coco.py
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
* fix yolox_s yolox_tiny
* fix tiny
* fix tiny
* simple tiny
---------
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
2023-02-10 10:50:59 +08:00
4e8bf17c90
[Improve] Beautify the YOLOv7 configuration ( #506 )
...
* Beautify the YOLOv7 configuration
* yolov7 config
* Update configs/yolov7/yolov7_l_syncbn_fast_8x16b-300e_coco.py
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
* Update configs/yolov7/yolov7_tiny_syncbn_fast_8x16b-300e_coco.py
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
* Update configs/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco.py
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
* Update configs/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco.py
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
* Update configs/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco.py
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
* Update configs/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco.py
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
* Beautify the YOLOv7 configuration
---------
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
2023-02-10 10:18:57 +08:00
d8b1353691
[Improve] Beautify YOLOv6 all configs ( #539 )
...
* Beauty YOLOv6 config
* Beauty YOLOv6 config
* Beauty config
* Beauty config
2023-02-10 10:13:47 +08:00
ff3e89809e
[DOC] Fix error link ( #537 )
...
* Fix error link
* Fix link
* Fix lint
2023-02-10 10:06:17 +08:00
e966ce4e60
[Improve] Beauty RTMDet config ( #531 )
...
* beauty rtmdet config
* format
2023-02-09 19:08:21 +08:00
82d288f5d4
[Improve] Beauty YOLOv6 head `gt_instances_preprocess` ( #532 )
...
* beauty yolov6 head preprocess
* add >0
* format
* add ut
* move path
* format
2023-02-09 19:05:28 +08:00
ccb8315ff3
[Enchance] judge `metainfo` is lower ( #535 )
...
* judge metainfo is lower
* update
* update
* update
2023-02-09 09:46:59 +08:00
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
031e7450bc
[Happy New Year] TensorRT + DeepStream Support. ( #485 )
...
* [Happy New Years] TensorRT + DeepStream Support.
* Add deepstream config
* pre-commit fix
* Fix name
* [Happy New Years] TensorRT + DeepStream Support.
* Add deepstream config
* pre-commit fix
* Fix name
* Add config
* Add rtmdet deepstream
2023-02-08 11:07:46 +08:00
4a7228a5cc
Fix rtmdet decoder in easydeploy ( #519 )
2023-02-07 14:45:27 +08:00
e90c369f9d
[Docs] Fix links in YOLOv8 README ( #517 )
...
* Update link
* Fix
2023-02-07 10:09:51 +08:00
c3acf42db4
Beautify the YOLOv8 configuration ( #516 )
...
* Update yolov5_s-v61_syncbn_8xb16-300e_coco.py
* Update yolov8_s_syncbn_fast_8xb16-500e_coco.py
* Update yolov8_m_syncbn_fast_8xb16-500e_coco.py
* Update yolov8_l_syncbn_fast_8xb16-500e_coco.py
* Update yolov8_s_syncbn_fast_8xb16-500e_coco.py
* Add todo
* Update yolov8_s_syncbn_fast_8xb16-500e_coco.py
* Update transforms.py
2023-02-06 19:39:39 +08:00
f54e5603fd
[Enchance] Extending `DetDataPreprocessor` flexibility ( #511 )
...
* Extending DetDataPreprocessor flexibility
* update
* add cast_data
2023-02-06 17:47:22 +08:00
1dee9eed6e
[Docs] How to specify specific GPU training and inference ( #503 )
...
* 中文版指定GPU训练
* 删去不必要文件
* typo
* rebase dev
* add test example
* add english version
* fix format
* english typo
* Update docs/zh_cn/advanced_guides/how_to.md
Co-authored-by: Range King <RangeKingHZ@gmail.com>
* Update docs/zh_cn/advanced_guides/how_to.md
Co-authored-by: Range King <RangeKingHZ@gmail.com>
---------
Co-authored-by: Range King <RangeKingHZ@gmail.com>
2023-02-06 10:12:04 +08:00
6acde82ec8
Fix typo for assigner visualization ( #509 )
2023-02-04 13:46:14 +08:00
8237f19bf8
Added the prompt to submit the pull request ( #508 )
2023-02-04 11:49:58 +08:00
5f2b08cf5a
add model structure graph of yolov7 in readme ( #504 )
2023-02-03 20:01:05 +08:00
79f0aae555
Beautify the YOLOv5 configuration ( #501 )
...
* refactor_config
2023-02-03 14:28:35 +08:00
74558aa2f7
Use official isort
2023-01-31 14:50:10 +08:00
77d9ad0c6b
[CI]: fix isort version issue in lint ( #492 )
...
* fix lint
* fix-lint
2023-01-29 17:48:54 +08:00
e62c8c4593
Bump version to 0.4.0
...
Bump version to 0.4.0
2023-01-18 19:54:21 +08:00
d8b13538dc
Add v0.4.0 Changelog ( #477 )
...
* Add v0.4.0 changelog
* update
* fix
* fix
* fix
* update
* update
* add url
2023-01-18 19:43:27 +08:00
ac27f900e3
[Docs] Refine README ( #482 )
...
* add emoji in README
* update
* update
* update1
* update1
* Add banner
* minor fix
* adjust position
* add toc
* update zh_CN
* update zh_CN
* test
* update
* test
* test
* update
* update
* update
* update
* add banner in README_zh-CN
* replace emoji
* minor fix
* remove some videos
* Update README_zh-CN.md
Co-authored-by: huanghaian <huanghaian@sensetime.com>
2023-01-18 19:38:34 +08:00
51d30a2837
[Docs] Update `article.md` and `model_zoo.md` ( #481 )
...
* Update article.md
* Update model_zoo.md
* Update model_zoo.md
2023-01-18 15:23:31 +08:00
6bdfc0da26
[Feature] Add a tool for scheduler visualization ( #479 )
...
* Create vis_scheduler.py
* add docs
* Update .gitignore
* Update useful_tools.md
* add source link
* Add TODO
2023-01-18 15:03:02 +08:00
6f478e1ae0
[Bug] Support RTMDet P6 model ( #480 )
2023-01-18 15:02:39 +08:00
da62ae7283
[Doc] Add PPYOLOE model structure ( #471 )
...
* Update README.md
Add PPYOLOE model structure
* Update README.md
* Update README.md
* Update README.md
* Update README.md
* Update README.md
* Update README.md
2023-01-18 14:32:20 +08:00
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
8eefed39ef
[Doc] Fix the installation step on get_started.md ( #474 )
2023-01-17 15:15:24 +08:00
c32ca4549f
[DOC] Add YOLOv8 docs ( #461 )
...
* Add YOLOv8 docs
* update
* update
* fix some error
* update en
* fix comment
* update
2023-01-17 15:12:02 +08:00
feef44da23
[Fix] Fix requirement about only ONNXRuntime without TensorRT ( #469 )
...
* Fix requirement about only onnxruntime without tensorrt
* Update projects/easydeploy/model/backendwrapper.py
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
* Update projects/easydeploy/model/backendwrapper.py
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
* Update projects/easydeploy/model/backendwrapper.py
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
* Update projects/easydeploy/model/backendwrapper.py
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
2023-01-16 19:36:49 +08:00
e66991fc6e
[Fix] Fix YOLOv8 graph and a lint issue ( #459 )
...
* add missing bg frame
* fix easydeploy lint
2023-01-12 16:00:46 +08:00
8e39252259
Support YOLOv8 deploy ( #456 )
2023-01-12 10:07:44 +08:00
550664d514
[Doc] Add the model structure graph of YOLOv8-P5 ( #455 )
...
* add YOLOv8 model structure figure
* Fix the layer name
2023-01-12 10:07:06 +08:00
935d710f79
[Feature] Support YOLOv8 inference ( #445 )
...
* 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: huanghaian <huanghaian@sensetime.com>
2023-01-11 19:01:06 +08:00
f1855ca618
[Feature] Add new YOLOX bbox coder for TensorRT-8 and fix TensorRT-7 bug ( #450 )
...
* Add yolox bbox decoder for tensorrt backend
* Fix tensorrt7+ bug
2023-01-11 17:10:04 +08:00
fd0f07b8ac
[Fix] Fix import error in `optimize_anchors.py` ( #452 )
...
* [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: HinGwenWoong <peterhuang0323@qq.com>
2023-01-11 17:09:31 +08:00
c682ae82c6
adjust the minimum supported python version to 3.9 ( #449 )
2023-01-09 18:31:37 +08:00
b0cf073241
Bump version to v0.3.0
...
Bump version to v0.3.0
2023-01-08 15:48:53 +08:00
9c6b4fedc8
Add v0.3.0 changelog ( #440 )
...
* bump version to v0.3.0
* add v7 cat demo config
* update mmdet version
* update
* fix topk out of range error
* update
* add changelog.md
* update
* update
* update
* update
* update
2023-01-08 15:31:58 +08:00
fc107b8997
[Docs] Add an example project to 'projects\' folder ( #401 )
...
* add_example_project
* renew readme
* Update projects/example_project/README.md
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
* Update projects/example_project/README.md
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
* Update projects/example_project/README.md
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
* Update projects/example_project/README.md
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
* Update projects/example_project/README.md
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
* Update projects/example_project/README.md
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
* Update projects/example_project/dummy/dummy_resnet.py
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
* Update projects/example_project/README.md
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
* Update projects/example_project/dummy/dummy_resnet.py
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
* Update projects/example_project/README.md
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
* renew to yolov5
* Update projects/example_project/dummy/dummy_yolov5cspdarknet.py
Co-authored-by: Range King <RangeKingHZ@gmail.com>
* Update projects/example_project/README.md
Co-authored-by: Range King <RangeKingHZ@gmail.com>
* Update projects/example_project/dummy/dummy_yolov5cspdarknet.py
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
* fix issue
* Update projects/example_project/dummy/dummy_yolov5cspdarknet.py
* Update projects/example_project/README.md
* Update projects/example_project/README.md
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>
2023-01-08 14:51:39 +08:00
a631370cb3
Update model graphs ( #442 )
2023-01-07 17:44:19 +08:00
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
7d07e1a780
Update yolo_detector.py ( #441 )
...
将 YOLOX -> YOLO
2023-01-06 19:20:24 +08:00
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
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
yechenzhi
Range King
Yue Sun
Youfu
tianlei
HinGwenWoong
Nioolek
Haian Huang(深度眸)
tripleMu
布鲁瓦丝
Audrey528
LinXiaoZheng
Yijie Zheng
Haonan
Seperendity
Jing Tang