ultralytics/yolov3: v9.1 - YOLOv5 Forward Compatibility Updates
Creators
- Glenn Jocher1
- Yonghye Kwon2
- guigarfr
- perry04183
- Josh Veitch-Michaelis4
- Ttayu5
- Daniel Suess6
- Fatih Baltacı
- Gabriel Bianconi7
- IlyaOvodov8
- Marc
- e960314139
- Chang Lee
- Dustin Kendall10
- Falak11
- Francisco Reveriano12
- FuLin
- GoogleWiki
- Jason Nataprawira13
- Jeremy Hu
- LinCoce
- LukeAI
- NanoCode012
- NirZarrabi
- Oulbacha Reda14
- Piotr Skalski15
- SergioSanchezMontesUAM
- Shiwei Song
- Thomas Havlik
- Timothy M. Shead16
- 1. @ultralytics
- 2. MarkAny
- 3. State Grid Electric Power Research Institute
- 4. University of Wisconsin-Madison
- 5. Image Algorigthm Engineer
- 6. @silverpond
- 7. Scalar Research
- 8. Elvees NeoTek JSC elveesneotek.ru
- 9. NCTU College of AI
- 10. Continental
- 11. Infocusp
- 12. Duke Applied Machine Laboratory
- 13. Ritsumeikan University
- 14. Polytechnique Montréal
- 15. @VirtusLab
- 16. Sandia National Laboratories
Description
This release is a minor update implementing numerous bug fixes, feature additions and performance improvements from https://github.com/ultralytics/yolov5 to this repo. Models remain unchanged from v9.0 release.
Branch NoticeThe ultralytics/yolov3 repository is now divided into two branches:
- Master branch: Forward-compatible with all YOLOv5 models and methods (recommended).
$ git clone https://github.com/ultralytics/yolov3 # master branch (default)
- Archive branch: Backwards-compatible with original darknet *.cfg models (⚠️ no longer maintained).
$ git clone -b archive https://github.com/ultralytics/yolov3 # archive branch
<img src="https://user-images.githubusercontent.com/26833433/100382066-c8bc5200-301a-11eb-907b-799a0301595e.png" width="800">
** GPU Speed measures end-to-end time per image averaged over 5000 COCO val2017 images using a V100 GPU with batch size 32, and includes image preprocessing, PyTorch FP16 inference, postprocessing and NMS. EfficientDet data from google/automl at batch size 8.
Pretrained Checkpoints Model AP<sup>val</sup> AP<sup>test</sup> AP<sub>50</sub> Speed<sub>GPU</sub> FPS<sub>GPU</sub> params FLOPS YOLOv3 43.3 43.3 63.0 4.8ms 208 61.9M 156.4B YOLOv3-SPP 44.3 44.3 64.6 4.9ms 204 63.0M 157.0B YOLOv3-tiny 17.6 34.9 34.9 1.7ms 588 8.9M 13.3B AP<sup>test</sup> denotes COCO test-dev2017 server results, all other AP results denote val2017 accuracy. All AP numbers are for single-model single-scale without ensemble or TTA. Reproduce mAP by python test.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65
Speed<sub>GPU</sub> averaged over 5000 COCO val2017 images using a GCP n1-standard-16 V100 instance, and includes image preprocessing, FP16 inference, postprocessing and NMS. NMS is 1-2ms/img. Reproduce speed by python test.py --data coco.yaml --img 640 --conf 0.25 --iou 0.45
All checkpoints are trained to 300 epochs with default settings and hyperparameters (no autoaugmentation).
Test Time Augmentation (TTA) runs at 3 image sizes. Reproduce TTA** by python test.py --data coco.yaml --img 832 --iou 0.65 --augment
Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7
. To install run:
$ pip install -r requirements.txt
Files
ultralytics/yolov3-v9.1.zip
Files
(1.0 MB)
Name | Size | Download all |
---|---|---|
md5:03cb1c6ca8206cc435568a806e944a0d
|
1.0 MB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/ultralytics/yolov3/tree/v9.1 (URL)