v0.3.0
版本发布时间: 2023-01-08 15:50:54
open-mmlab/mmyolo最新发布版本:v0.6.0(2023-08-15 13:20:22)
v0.3.0 (8/1/2023)
Highlights
- 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
New Features
- 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)
Bug Fixes
- 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)
Improvements
- 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)
Contributors
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