Published October 29, 2020
| Version v3.1
Software
Open
ultralytics/yolov5: v3.1 - Bug Fixes and Performance Improvements
Creators
- Glenn Jocher1
- Alex Stoken2
- Jirka Borovec3
- NanoCode012
- ChristopherSTAN
- Liu Changyu4
- Laughing
- tkianai5
- Adam Hogan
- lorenzomammana6
- yxNONG
- AlexWang1900
- Laurentiu Diaconu7
- Marc
- wanghaoyang0106
- ml5ah
- Doug
- Francisco Ingham
- Frederik
- Guilhen
- Hatovix
- Jake Poznanski
- Jiacong Fang
- Lijun Yu 于力军8
- changyu98
- Mingyu Wang
- Naman Gupta
- Osama Akhtar9
- PetrDvoracek
- Prashant Rai
- 1. @ultralytics
- 2. Jacobs JETS @ NASA Johnson Space Center
- 3. CTU in Prague
- 4. Dakewe Biotech Co., Ltd.
- 5. 首席在吗?需要剪发
- 6. University of Milan-Bicocca
- 7. innAIte technologies
- 8. Carnegie Mellon University
- 9. National University of Sciences and Technology
Description
This release aggregates various minor bug fixes and performance improvements since the main v3.0 release and incorporates PyTorch 1.7.0 compatibility updates. v3.1 models share weights with v3.0 models but contain minor module updates (inplace fields for nn.Hardswish() activations) for native PyTorch 1.7.0 compatibility.
- 'GIoU' hyperparameter has been renamed to 'box' to better reflect a criteria-agnostic regression loss term (https://github.com/ultralytics/yolov5/pull/1120)
- PyTorch 1.7 compatibility update.
torch>=1.6.0required,torch>=1.7.0recommended (https://github.com/ultralytics/yolov5/pull/1233) - GhostConv module bug fix (https://github.com/ultralytics/yolov5/pull/1176)
- Rectangular padding min stride bug fix from 64 to 32 (https://github.com/ultralytics/yolov5/pull/1165)
- Mosaic4 bug fix (https://github.com/ultralytics/yolov5/pull/1021)
- Logging directory runs/exp bug fix (https://github.com/ultralytics/yolov5/pull/978)
- Various additional
- PyTorch Hub functionality with YOLOv5 .autoshape() method added (https://github.com/ultralytics/yolov5/pull/1210)
- Autolabelling addition and standardization across detect.py and test.py (https://github.com/ultralytics/yolov5/pull/1182)
- Precision-Recall Curve automatic plotting when testing (https://github.com/ultralytics/yolov5/pull/1107)
- Self-host VOC dataset for more reliable access and faster downloading (https://github.com/ultralytics/yolov5/pull/1077)
- Adding option to output autolabel confidence with --save-conf in test.py and detect.py (https://github.com/ultralytics/yolov5/pull/994)
- Google App Engine deployment option (https://github.com/ultralytics/yolov5/pull/964)
- Infinite Dataloader for faster training (https://github.com/ultralytics/yolov5/pull/876)
- Various additional
Files
ultralytics/yolov5-v3.1.zip
Files
(3.2 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:40b45f47aa5695cedf25def94664d90c
|
3.2 MB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/ultralytics/yolov5/tree/v3.1 (URL)