ultralytics/yolov3: 43.1mAP@0.5:0.95 on COCO2014
Creators
- Glenn Jocher1
- Yonghye Kwon2
- guigarfr
- Josh Veitch-Michaelis3
- perry04184
- Ttayu5
- Marc
- Gabriel Bianconi6
- Fatih Baltacı
- Daniel Suess7
- 晨太狼
- 杨培文
- idow09
- WannaSeaU
- Wang Xinyu
- Timothy M. Shead8
- Thomas Havlik
- Piotr Skalski9
- NirZarrabi
- LukeAI
- LinCoce
- Jeremy Hu
- IlyaOvodov
- GoogleWiki
- Francisco Reveriano10
- Falak11
- Dustin Kendall12
- 1. @ultralytics
- 2. Kwangwoon University
- 3. Liverpool John Moores University
- 4. State Grid Electric Power Research Institute
- 5. Image Algorigthm Engineer
- 6. Scalar Research
- 7. @silverpond
- 8. Sandia National Laboratories
- 9. Poland
- 10. Duke Applied Machine Laboratory
- 11. Infocusp
- 12. Continental
Description
This release requires PyTorch >= v1.4 to function properly. Please install the latest version from https://github.com/pytorch/pytorch/releases
Breaking ChangesThere are no breaking changes in this release.
Bug Fixes- Various
- Improved training and test ground truth and prediction plotting. https://github.com/ultralytics/yolov3/pull/1114
- Increased augmentation speed. https://github.com/ultralytics/yolov3/pull/1110
- Improved Tensorboard integration.
- Auto class hyperparameter update based on dataset class count.
- Inference time augmentation option added now with
--augment
argument in test.py and detect.py. - Rectangular training with
--rect
argument in train.py
https://cloud.google.com/deep-learning-vm/
Machine type: preemptible n1-standard-8 (8 vCPUs, 30 GB memory)
CPU platform: Intel Skylake
GPUs: K80 ($0.14/hr), T4 ($0.11/hr), V100 ($0.74/hr) CUDA with Nvidia Apex FP16/32
HDD: 300 GB SSD
Dataset: COCO train 2014 (117,263 images)
Model: yolov3-spp.cfg
Command: python3 train.py --data coco2017.data --img 416 --batch 32
--batch-size
img/s
epoch<br>time
epoch<br>cost
K80
1
32 x 2
11
175 min
$0.41
T4
1<br>2
32 x 2<br>64 x 1
41<br>61
48 min<br>32 min
$0.09<br>$0.11
V100
1<br>2
32 x 2<br>64 x 1
122<br>178
16 min<br>11 min
$0.21<br>$0.28
2080Ti
1<br>2
32 x 2<br>64 x 1
81<br>140
24 min<br>14 min
-<br>-
mAP
<i></i>
Size
COCO mAP<br>@0.5...0.95
COCO mAP<br>@0.5
YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>YOLOv3-SPP-ultralytics
320
14.0<br>28.7<br>30.5<br>37.7
29.1<br>51.8<br>52.3<br>56.8
YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>YOLOv3-SPP-ultralytics
416
16.0<br>31.2<br>33.9<br>41.2
33.0<br>55.4<br>56.9<br>60.6
YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>YOLOv3-SPP-ultralytics
512
16.6<br>32.7<br>35.6<br>42.6
34.9<br>57.7<br>59.5<br>62.4
YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>YOLOv3-SPP-ultralytics
608
16.6<br>33.1<br>37.0<br>43.1
35.4<br>58.2<br>60.7<br>62.8
TODO (help and PR's welcome!)
- Add iOS App inference to photos and videos in Camera Roll, as well as 'Flexible', or at least rectangular inference. https://github.com/ultralytics/yolov3/issues/224
Files
ultralytics/yolov3-v7.zip
Files
(1.4 MB)
Name | Size | Download all |
---|---|---|
md5:f3b90086de50ba8aca2eab6267449664
|
1.4 MB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/ultralytics/yolov3/tree/v7 (URL)