Full implementation of YOLOv3 in PyTorch.
[Paper]
[Original Implementation]
git clone https://github.com/BobLiu20/YOLOv3_PyTorch.git
cd YOLOv3_PyTorch
pip3 install -r requirements.txt --user
cd data/
bash get_coco_dataset.sh
darknet53_weights_pytorch.pth
to wegihts
folder in this project.
training/params.py
YOUR_WORKING_DIR
to your working directory. Use for save model and tmp file.cd training
python training.py params.py
# please install tensorboard in first
python -m tensorboard.main --logdir=YOUR_WORKING_DIR
official_yolov3_weights_pytorch.pth
to wegihts
folder in this project.
cd evaluate
python eval_coco.py params.py
Please download pretrained weights official_yolov3_weights_pytorch.pth
or use yourself checkpoint.
cd test
python test_images.py params.py
You can got result images in output folder.
Please download pretrained weights official_yolov3_weights_pytorch.pth
or use yourself checkpoint.
cd test
python test_fps.py params.py
Imp. | Backbone | Input Size | Batch Size | Inference Time | FPS |
---|---|---|---|---|---|
Paper | Darknet53 | 320 | 1 | 22ms | 45 |
Paper | Darknet53 | 416 | 1 | 29ms | 34 |
Paper | Darknet53 | 608 | 1 | 51ms | 19 |
Our | Darknet53 | 416 | 1 | 28ms | 36 |
Our | Darknet53 | 416 | 8 | 17ms | 58 |
@article{yolov3,
title={YOLOv3: An Incremental Improvement},
author={Redmon, Joseph and Farhadi, Ali},
journal = {arXiv},
year={2018}
}