zhanghanduo / yolo3_pytorch

Yolo3 Implementation in Pytorch using COCO and BDD100K dataset. Forked from https://github.com/BobLiu20/YOLOv3_PyTorch.git. For my own fun, so the introduction is not accurate.

YOLO version3 in Pytorch

Full implementation of YOLO version3 in PyTorch, including training, evaluation, simple deployment(developing).

Overview

YOLOv3: An Incremental Improvement

[Paper]
[Original Implementation]

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 for details.

Training

Download pretrained weights

1. See weights readme for detail.
2. Download pretrained yolo3 full wegiths from Google Drive or Baidu Drive
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   

Evaluate

Download pretrained weights

1. See weights readme for detail.
2. Download pretrained yolo3 full wegiths from Google Drive or Baidu Drive
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

Roadmap

• Yolov3 training
• 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
• PyTorch-YOLOv3: Thanks for Evaluate and YOLO loss code

yolo3_pytorch's Issues

有关数据集的问题

没有找到你的data文件夹，请问你的coco数据集是用2017的coco还是2014的coco?
并且，bdd100k数据集，一共有很多文件，你都下载了哪些进行了训练呢？

请问您的mAP是哪个数据集的测试结果？是用的哪一种测量方法？（07voc/12voc/coco0.5/coco0.5：095）

您好，因为我最近也在做bdd100k的检测工作，看到您的mAP实在是让我惊讶不已，我所使用的yolo3的backbone是mobilenetv2，但是在bdd100k上的mAP只有35而已，评价标准是使用的voc07的方法

test

Traceback (most recent call last):
File "test_images.py", line 158, in
main()
File "test_images.py", line 154, in main
test(config)
File "test_images.py", line 126, in test
plt.text(x1, y1, s=classes[int(cls_pred)], color='white',
IndexError: list index out of range

asking favour for darknet21

excuse me , i got a need for faster detection , could you please afford a darknet21 pretrained model in this pytorch implementation ?

BDD100k

Hey, I just wanted to ask that have you done training of Bdd100k data with YOLO3 . and if you have can you please give me that link of all the files related to that.

Trained with BDD dataset or COCO?

Hi, I'm impressed by this repo and I'm using the pretrained models with joy.

However, I'm wondering if the pretrained models are trained with BDD or COCO.

Could you give me an answer?

请问关于训练loss的问题

您好，为什么我使用coco的train14训练，loss一开始就是0.0几，后面也一直是0.0几呢？