Yolo3 Implementation in Pytorch using COCO and BDD100K datas

# YOLO version3 in Pytorch Full implementation of YOLO version3 in PyTorch, including training, evaluation, simple deployment(developing). ## Overview #### YOLOv3: An Incremental Improvement [[Paper]](https://pjreddie.com/media/files/papers/YOLOv3.pdf) [[Original Implementation]](https://github.com/pjreddie/darknet) #### Motivation Implement YOLOv3 and darknet53 without original darknet cfg parser. It is easy to custom your backbone network. Such as resnet, densenet... Also decide to develop custom structure (like grayscale pretrained model) ## Installation ##### Environment * pytorch >= 0.4.0 * python >= 3.6.0 ##### Get code ``` git clone https://github.com/zhanghanduo/yolo3_pytorch.git cd YOLOv3_PyTorch pip3 install -r requirements.txt --user ``` ##### Download COCO dataset ``` cd data/ bash get_coco_dataset.sh ``` ##### Download BDD dataset Please visit [BDD100K](https://github.com/ucbdrive/bdd-data) for details. ## Training ##### Download pretrained weights 1. See [weights readme](weights/README.md) for detail. 2. Download pretrained yolo3 full wegiths from [Google Drive](https://drive.google.com/file/d/1SnFAlSvsx37J7MDNs3WWLgeKY0iknikP/view?usp=sharing) or [Baidu Drive](https://pan.baidu.com/s/1YCcRLPWPNhsQfn5f8bs_0g) 3. Move downloaded file ```official_yolov3_weights_pytorch.pth``` to ```weights``` folder in this project. ##### Modify training parameters 1. Review config file ```training/params.py``` 2. Replace ```YOUR_WORKING_DIR``` to your working directory. Use for save model and tmp file. 3. Adjust your GPU device. See parallels. 4. Adjust other parameters. ##### Start training ``` cd training python training.py params.py ``` ##### Option: Visualizing training ``` # please install tensorboard in first python -m tensorboard.main --logdir=YOUR_WORKING_DIR ``` <p><img src="common/loss_curve.png"\></p> ## Evaluate ##### Download pretrained weights 1. See [weights readme](weights/README.md) for detail. 2. Download pretrained yolo3 full wegiths from [Google Drive](https://drive.google.com/open?id=1Bm_CLv9hP3mMQ5cyerKRjvt7_t1duvjI) or [Baidu Drive](https://pan.baidu.com/s/1gx-XRUE1NTfIMKkQ1L0awQ) 3. Move downloaded file ```yolov3_weights_pytorch.pth``` to ```wegihts``` folder in this project. ##### Start evaluate ``` cd evaluate python eval.py params.py python eval_coco.py params.py ``` <p align="center"><img src="https://pjreddie.com/media/image/Screen_Shot_2018-03-24_at_10.48.42_PM.png" width="480"\></p> #### Roadmap - [x] Yolov3 training - [x] Yolov3 evaluation - [ ] Add backbone network other than Darknet - [ ] Able to adapt 3-channel image to 1-channel input ## Credit ``` @article{yolov3, title={YOLOv3: An Incremental Improvement}, author={Redmon, Joseph and Farhadi, Ali}, journal = {arXiv}, year={2018} } ``` ## Reference * [darknet](https://github.com/pjreddie/darknet) * [PyTorch-YOLOv3](https://github.com/eriklindernoren/PyTorch-YOLOv3): Thanks for Evaluate and YOLO loss code