YOLOv3-PyTorch

Contents

• Introduction
• Getting Started
  • Requirements
  • From PyPI
  • Local Install
• Inference (TODO)
• All pretrained model weights
• How Test and Train
  • Test yolov3_tiny_voc model
  • Train yolov3_tiny_voc model
  • Resume train yolov3_tiny_voc model
• Result
• Contributing
• Credit
  • YOLOv3: An Incremental Improvement

Introduction

This repository contains an op-for-op PyTorch reimplementation of YOLOv3: An Incremental Improvement.

Getting Started

Requirements

• Python 3.10+
• PyTorch 2.0.0+
• CUDA 11.8+
• Ubuntu 22.04+

From PyPI

pip3 install yolov3_pytorch -i https://pypi.org/simple

Local Install

git clone https://github.com/Lornatang/YOLOv3-PyTorch.git
cd YOLOv3-PyTorch
pip3 install -r requirements.txt
pip3 install -e .

All pretrained model weights

• Google Driver
• Baidu Driver

Inference (e.g YOLOv3_Tiny-VOC0712)

# Download YOLOv3_Tiny-VOC0712 model weights to `./results/pretrained_models`
wget https://github.com/Lornatang/YOLOv3-PyTorch/releases/download/0.1.5/YOLOv3_Tiny-VOC0712-20231107.pth.tar -O ./resutls/pretrained_models/YOLOv3_Tiny-VOC0712-20231107.pth.tar
python3 ./tools/inference.py ./data/examples/dog.jpg
# Result will be saved to `./results/predict/YOLOv3_Tiny-VOC0712/dog.jpg`

Test

VOC0712

# Download dataset to `./data`
cd ./scripts
bash ./process_voc0712_dataset.sh
cd ..
# Download pretrained model weights to `./results/pretrained_models`
wget https://github.com/Lornatang/YOLOv3-PyTorch/releases/download/0.1.5/YOLOv3_Tiny-VOC0712-20231107.pth.tar -O ./resutls/pretrained_models/YOLOv3_Tiny-VOC0712-20231107.pth.tar
python3 ./tools/test.py ./configs/YOLOv3_Tiny-VOC0712.yaml

Results

COCO2014

VOC

Train

VOC0712

# Download dataset to `./data`
cd ./scripts
bash ./process_voc0712_dataset.sh
cd ..
# Download pretrained model weights to `./results/pretrained_models`
wget https://github.com/Lornatang/YOLOv3-PyTorch/releases/download/0.1.5/YOLOv3_Tiny-VOC0712-20231107.pth.tar -O ./resutls/pretrained_models/YOLOv3_Tiny-VOC0712-20231107.pth.tar
python3 ./tools/train.py ./configs/YOLOv3_Tiny-VOC0712.yaml

COCO2014 & COCO2017

# COCO2014
# Download dataset to `./data`
cd ./scripts
bash ./process_coco2014_dataset.sh
cd ..
# Download pretrained model weights to `./results/pretrained_models`
wget https://github.com/Lornatang/YOLOv3-PyTorch/releases/download/0.1.5/YOLOv3_Tiny-COCO2014-20231107.pth.tar -O ./resutls/pretrained_models/YOLOv3_Tiny-COCO2014-20231107.pth.tar
python3 ./tools/train.py ./configs/YOLOv3_Tiny-COCO2014.yaml

# COCO2017
# Download dataset to `./data`
cd ./scripts
bash ./process_coco2017_dataset.sh
cd ..
# Download pretrained model weights to `./results/pretrained_models`
wget https://github.com/Lornatang/YOLOv3-PyTorch/releases/download/0.1.5/YOLOv3_Tiny-COCO2017-20231107.pth.tar -O ./resutls/pretrained_models/YOLOv3_Tiny-COCO2017-20231107.pth.tar
python3 ./tools/train.py ./configs/YOLOv3_Tiny-COCO2017.yaml

Custom dataset

Details see CustomDataset.md.

Contributing

If you find a bug, create a GitHub issue, or even better, submit a pull request. Similarly, if you have questions, simply post them as GitHub issues.

I look forward to seeing what the community does with these models!

Credit

YOLOv3: An Incremental Improvement

Joseph Redmon, Ali Farhadi

Abstract
We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that’s pretty swell. It’s a little bigger than last time but more accurate. It’s still fast though, don’t worry. At 320 × 320 YOLOv3 runs in 22 ms at 28.2 mAP, as accurate as SSD but three times faster. When we look at the old .5 IOU mAP detection metric YOLOv3 is quite good. It achieves 57.9 AP50 in 51 ms on a Titan X, compared to 57.5 AP50 in 198 ms by RetinaNet, similar performance but 3.8× faster. As always, all the code is online at https://pjreddie.com/yolo/.

[Paper] [Project Webpage] [Authors' Implementation]

@article{yolov3,
  title={YOLOv3: An Incremental Improvement},
  author={Redmon, Joseph and Farhadi, Ali},
  journal = {arXiv},
  year={2018}
}