- Support RTMDet-R rotated object detection
- Support for using mask annotation to improve YOLOv8 object detection performance
- Support MMRazor searchable NAS sub-network as the backbone of YOLO series algorithm
- Support calling MMRazor to distill the knowledge of RTMDet
- MMYOLO document structure optimization, comprehensive content upgrade
- Improve YOLOX mAP and training speed based on RTMDet training hyperparameters
- Support calculation of model parameters and FLOPs, provide GPU latency data on T4 devices, and update Model Zoo
- Support test-time augmentation (TTA)
- Support RTMDet, YOLOv8 and YOLOv7 assigner visualization
- Support inference for RTMDet instance segmentation tasks (#583)
- Beautify the configuration file in MMYOLO and add more comments (#501, #506, #516, #529, #531, #539)
- Refactor and optimize documentation (#568, #573, #579, #584, #587, #589, #596, #599, #600)
- Support fast version of YOLOX (#518)
- Support DeepStream in EasyDeploy and add documentation (#485, #545, #571)
- Add confusion matrix drawing script (#572)
- Add single channel application case (#460)
- Support auto registration (#597)
- Support Box CAM of YOLOv7, YOLOv8 and PPYOLOE (#601)
- Add automated generation of MM series repo registration information and tools scripts (#559)
- Added YOLOv7 model structure diagram (#504)
- Add how to specify specific GPU training and inference files (#503)
- Add check if
metainfo
is all lowercase when training or testing (#535) - Add links to Twitter, Discord, Medium, YouTube, etc. (#555)
- Fix isort version issue (#492, #497)
- Fix type error of assigner visualization (#509)
- Fix YOLOv8 documentation link error (#517)
- Fix RTMDet Decoder error in EasyDeploy (#519)
- Fix some document linking errors (#537)
- Fix RTMDet-Tiny weight path error (#580)
- Update
contributing.md
- Optimize
DetDataPreprocessor
branch to support multitasking (#511) - Optimize
gt_instances_preprocess
so it can be used for other YOLO algorithms (#532) - Add
yolov7-e6e
weight conversion script (#570) - Reference YOLOv8 inference code modification PPYOLOE
A total of 22 developers contributed to this release.
Thank @triple-Mu, @isLinXu, @Audrey528, @TianWen580, @yechenzhi, @RangeKing, @lyviva, @Nioolek, @PeterH0323, @tianleiSHI, @aptsunny, @satuoqaq, @vansin, @xin-li-67, @VoyagerXvoyagerx, @landhill, @kitecats, @tang576225574, @HIT-cwh, @AI-Tianlong, @RangiLyu, @hhaAndroid
- Implemented YOLOv8 object detection model, and supports model deployment in projects/easydeploy
- Added Chinese and English versions of Algorithm principles and implementation with YOLOv8
- Added YOLOv8 and PPYOLOE model structure diagrams (#459, #471)
- Adjust the minimum supported Python version from 3.6 to 3.7 (#449)
- Added a new YOLOX decoder in TensorRT-8 (#450)
- Add a tool for scheduler visualization (#479)
- Fix
optimize_anchors.py
script import error (#452) - Fix the wrong installation steps in
get_started.md
(#474) - Fix the neck error when using the
RTMDet
P6 model (#480)
A total of 9 developers contributed to this release.
Thank @VoyagerXvoyagerx, @tianleiSHI, @RangeKing, @PeterH0323, @Nioolek, @triple-Mu, @lyviva, @Zheng-LinXiao, @hhaAndroid
- Implement fast version of RTMDet. RTMDet-s 8xA100 training takes only 14 hours. The training speed is 2.6 times faster than the previous version.
- Support PPYOLOE training
- Support
iscrowd
attribute training in YOLOv5 - Support YOLOv5 assigner result visualization
- Add
crowdhuman
dataset (#368) - Easydeploy support TensorRT inference (#377)
- Add
YOLOX
structure description (#402) - Add a feature for the video demo (#392)
- Support
YOLOv7
easy deploy (#427) - Add resume from specific checkpoint in CLI (#393)
- Set
metainfo
fields to lower case (#362, #412) - Add module combination doc (#349, #352, #345)
- Add docs about how to freeze the weight of backbone or neck (#418)
- Add don't used pre-training weights doc in
how_to.md
(#404) - Add docs about how to set the random seed (#386)
- Translate
rtmdet_description.md
document to English (#353) - Add doc of
yolov6_description.md
(#382, #372)
- Fix bugs in the output annotation file when
--class-id-txt
is set (#430) - Fix batch inference bug in
YOLOv5
head (#413) - Fix typehint in some heads (#415, #416, #443)
- Fix RuntimeError of
torch.cat()
expected a non-empty list of Tensors (#376) - Fix the device inconsistency error in
YOLOv7
training (#397) - Fix the
scale_factor
andpad_param
value inLetterResize
(#387) - Fix docstring graph rendering error of readthedocs (#400)
- Fix AssertionError when
YOLOv6
from training to val (#378) - Fix CI error due to
np.int
and legacy builder.py (#389) - Fix MMDeploy rewriter (#366)
- Fix MMYOLO unittest scope bug (#351)
- Fix
pad_param
error (#354) - Fix twice head inference bug (#342)
- Fix customize dataset training (#428)
- Update
useful_tools.md
(#384) - update the English version of
custom_dataset.md
(#381) - Remove context argument from the rewriter function (#395)
- deprecating
np.bool
type alias (#396) - Add new video link for custom dataset (#365)
- Export onnx for model only (#361)
- Add MMYOLO regression test yml (#359)
- Update video tutorials in
article.md
(#350) - Add deploy demo (#343)
- Optimize the vis results of large images in debug mode (#346)
- Improve args for
browse_dataset
and supportRepeatDataset
(#340, #338)
A total of 28 developers contributed to this release.
Thank @RangeKing, @PeterH0323, @Nioolek, @triple-Mu, @matrixgame2018, @xin-li-67, @tang576225574, @kitecats, @Seperendity, @diplomatist, @vaew, @wzr-skn, @VoyagerXvoyagerx, @MambaWong, @tianleiSHI, @caj-github, @zhubochao, @lvhan028, @dsghaonan, @lyviva, @yuewangg, @wang-tf, @satuoqaq, @grimoire, @RunningLeon, @hanrui1sensetime, @RangiLyu, @hhaAndroid
- Support YOLOv7 P5 and P6 model
- Support YOLOv6 ML model
- Support Grad-Based CAM and Grad-Free CAM
- Support large image inference based on sahi
- Add easydeploy project under the projects folder
- Add custom dataset guide
browse_dataset.py
script supports visualization of original image, data augmentation and intermediate results (#304)- Add flag to output labelme label file in
image_demo.py
(#288, #314) - Add
labelme2coco
script (#308, #313) - Add split COCO dataset script (#311)
- Add two examples of backbone replacement in
how-to.md
and updateplugin.md
(#291) - Add
contributing.md
andcode_style.md
(#322) - Add docs about how to use mim to run scripts across libraries (#321)
- Support
YOLOv5
deployment at RV1126 device (#262)
- Fix MixUp padding error (#319)
- Fix scale factor order error of
LetterResize
andYOLOv5KeepRatioResize
(#305) - Fix training errors of
YOLOX Nano
model (#285) - Fix
RTMDet
deploy error (#287) - Fix int8 deploy config (#315)
- Fix
make_stage_plugins
doc inbasebackbone
(#296) - Enable switch to deploy when create pytorch model in deployment (#324)
- Fix some errors in
RTMDet
model graph (#317)
- Add option of json output in
test.py
(#316) - Add area condition in
extract_subcoco.py
script (#286) - Deployment doc translation (#289)
- Add YOLOv6 description overview doc (#252)
- Improve
config.md
(#297, #303) 6Add mosaic9 graph in docstring (#307) - Improve
browse_coco_json.py
script args (#309) - Refactor some functions in
dataset_analysis.py
to be more general (#294)
A total of 14 developers contributed to this release.
Thank @fcakyon, @matrixgame2018, @MambaWong, @imAzhou, @triple-Mu, @RangeKing, @PeterH0323, @xin-li-67, @kitecats, @hanrui1sensetime, @AllentDan, @Zheng-LinXiao, @hhaAndroid, @wanghonglie
- Support CBAM plug-in and provide plug-in documentation (#246)
- Add YOLOv5 P6 model structure diagram and related descriptions (#273)
- Fix training failure when saving best weights based on mmengine 0.3.1
- Fix
add_dump_metric
error based on mmdet 3.0.0rc3 (#253) - Fix backbone does not support
init_cfg
issue (#272) - Change typing import method based on mmdet 3.0.0rc3 (#261)
featmap_vis_demo
support for folder and url input (#248)- Deploy docker file refinement (#242)
A total of 10 developers contributed to this release.
Thank @kitecats, @triple-Mu, @RangeKing, @PeterH0323, @Zheng-LinXiao, @tkhe, @weikai520, @zytx121, @wanghonglie, @hhaAndroid
- Support YOLOv5/YOLOv6/YOLOX/RTMDet deployments for ONNXRuntime and TensorRT
- Support YOLOv6 s/t/n model training
- YOLOv5 supports P6 model training which can input 1280-scale images
- YOLOv5 supports VOC dataset training
- Support PPYOLOE and YOLOv7 model inference and official weight conversion
- Add YOLOv5 replacement backbone tutorial in How-to documentation
- Add
optimize_anchors
script (#175) - Add
extract_subcoco
script (#186) - Add
yolo2coco
conversion script (#161) - Add
dataset_analysis
script (#172) - Remove Albu version restrictions (#187)
- Fix the problem that
cfg.resume
does not work when set (#221) - Fix the problem of not showing bbox in feature map visualization script (#204)
- uUpdate the metafile of RTMDet (#188)
- Fix a visualization error in
test_pipeline
(#166) - Update badges (#140)
- Optimize Readthedoc display page (#209)
- Add docstring for module structure diagram for base model (#196)
- Support for not including any instance logic in LoadAnnotations (#161)
- Update
image_demo
script to support folder and url paths (#128) - Update pre-commit hook (#129)
- Translate
yolov5_description.md
,yolov5_tutorial.md
andvisualization.md
into English (#138, #198, #206) - Add deployment-related Chinese documentation (#220)
- Update
config.md
,faq.md
andpull_request_template.md
(#190, #191, #200) - Update the
article
page (#133)
A total of 14 developers contributed to this release.
Thank @imAzhou, @triple-Mu, @RangeKing, @PeterH0323, @xin-li-67, @Nioolek, @kitecats, @Bin-ze, @JiayuXu0, @cydiachen, @zhiqwang, @Zheng-LinXiao, @hhaAndroid, @wanghonglie
Based on MMDetection's RTMDet high precision and low latency object detection algorithm, we have also released RTMDet and provided a Chinese document on the principle and implementation of RTMDet.
- Support RTMDet
- Support for backbone customization plugins and update How-to documentation (#75)
- Fix some documentation errors (#66, #72, #76, #83, #86)
- Fix checkpoints link error (#63)
- Fix the bug that the output of
LetterResize
does not meet the expectation when usingimscale
(#105)
- Reducing the size of docker images (#67)
- Simplifying
Compose
Logic inBaseMixImageTransform
(#71) - Supports dump results in
test.py
(#84)
A total of 13 developers contributed to this release.
Thank @wanghonglie, @hhaAndroid, @yang-0201, @PeterH0323, @RangeKing, @satuoqaq, @Zheng-LinXiao, @xin-li-67, @suibe-qingtian, @MambaWong, @MichaelCai0912, @rimoire, @Nioolek
We have released MMYOLO open source library, which is based on MMEngine, MMCV 2.x and MMDetection 3.x libraries. At present, the object detection has been realized, and it will be expanded to multi-task in the future.
- Support YOLOv5/YOLOX training, support YOLOv6 inference. Deployment will be supported soon.
- Refactored YOLOX from MMDetection to accelerate training and inference.
- Detailed introduction and advanced tutorials are provided, see the English tutorial.