Name | Modified | Size | Downloads / Week |
---|---|---|---|
Parent folder | |||
yolov3-tiny.pt | 2021-01-08 | 17.8 MB | |
yolov3-spp.pt | 2021-01-08 | 126.3 MB | |
yolov3.pt | 2021-01-08 | 124.2 MB | |
README.md | 2020-12-06 | 3.3 kB | |
v9.0 - YOLOv5 Forward Compatibility Release.tar.gz | 2020-12-06 | 1.0 MB | |
v9.0 - YOLOv5 Forward Compatibility Release.zip | 2020-12-06 | 1.0 MB | |
Totals: 6 Items | 270.4 MB | 0 |
This release is a major update to the https://github.com/ultralytics/yolov3 repository that brings forward-compatibility with YOLOv5, and incorporates numerous bug fixes, feature additions and performance improvements from https://github.com/ultralytics/yolov5 to this repo.
Branch Notice
The ultralytics/yolov3 repository is now divided into two branches: * Master branch: Forward-compatible with all YOLOv5 models and methods (recommended).
:::bash
$ git clone https://github.com/ultralytics/yolov3 # master branch (default)
-
Archive branch: Backwards-compatible with original darknet *.cfg models (⚠️ no longer maintained).
:::bash $ git clone -b archive https://github.com/ultralytics/yolov3 # archive branch
** 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 | APval | APtest | AP50 | SpeedGPU | FPSGPU | 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 |
** APtest 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
SpeedGPU 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
Requirements
Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7
. To install run:
:::bash
$ pip install -r requirements.txt