• 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    迪恩网络公众号

jwchoi384/Gaussian_YOLOv3: Gaussian YOLOv3: An Accurate and Fast Object Detector ...

原作者: [db:作者] 来自: 网络 收藏 邀请

开源软件名称(OpenSource Name):

jwchoi384/Gaussian_YOLOv3

开源软件地址(OpenSource Url):

https://github.com/jwchoi384/Gaussian_YOLOv3

开源编程语言(OpenSource Language):

C 89.2%

开源软件介绍(OpenSource Introduction):

Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving

Gaussian YOLOv3 implementation

This repository contains the code for our ICCV 2019 Paper

The proposed algorithm is implemented based on the YOLOv3 official code.

The provided example weight file ("Gaussian_yolov3_BDD.weights") is not the weight file used in the paper, but newly trained weight for release code validation. Because this weight file is more accurate than the weight used in the paper, we provide this file in the repository.

Poster

Citation

@InProceedings{Choi_2019_ICCV,
author = {Choi, Jiwoong and Chun, Dayoung and Kim, Hyun and Lee, Hyuk-Jae},
title = {Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}

Requirements

The code was tested on

Ubuntu 16.04, NVIDIA GTX 1080 Ti with CUDA 8.0 and cuDNNv7, OpenCV 3.4.0

Ubuntu 16.04, NVIDIA Titan Xp with CUDA 9.0 and cuDNNv7, OpenCV 3.3.0

Setup

Please see the YOLOv3 website instructions setup

Dataset

We tested our algorithm using Berkeley deep drive (BDD) dataset.

If you want to use BDD dataset, please see BDD website and download the dataset.

Training

For training, you must make image list file (e.g., "train_bdd_list.txt") and ground-truth data. Please see these websites: YOLOv3, How to train YOLO

List files ("train_bdd_list.txt", "val_bdd_list.txt", "test_bdd_list.txt") in the repository are an example. You must modify the directory of the file name in the list to match the path where the dataset is located on your computer.

Download pre-trained weights darknet53.conv.74

Download the code

git clone https://github.com/jwchoi384/Gaussian_YOLOv3
cd Gaussian_YOLOv3

Compile the code

make

Set batch=64 and subdivisions=16 in the cfg file.

We used 4 gpus in our experiment. If your computer runs out of GPU memory when training, please increase subdivision size in the cfg file.

Start training by using the command line

./darknet detector train cfg/BDD.data cfg/Gaussian_yolov3_BDD.cfg darknet53.conv.74

If you want to use multiple gpus,

./darknet detector train cfg/BDD.data cfg/Gaussian_yolov3_BDD.cfg darknet53.conv.74 -gpus 0,1,2,3

Inference

Download the Gaussian_YOLOv3 example weight file. Gaussian_yolov3_BDD.weights

Set batch=1 and subdivisions=1 in the cfg file.

Run the following commands.

  1. make
  2. ./darknet detector test cfg/BDD.data cfg/Gaussian_yolov3_BDD.cfg Gaussian_yolov3_BDD.weights data/example.jpg

You can see the result:

Evaluation

Download the Gaussian_YOLOv3 example weight file. Gaussian_yolov3_BDD.weights

For evaluation, you MUST change the batch and subdivision size in cfg file. Like this: batch = 1, subdivision = 1

Run the following commands. You can get a detection speed of more than 42 FPS.

  1. make

  2. ./darknet detector valid cfg/BDD.data cfg/Gaussian_yolov3_BDD.cfg Gaussian_yolov3_BDD.weights

  3. cd bdd_evaluation/ (We got this code from https://github.com/ucbdrive/bdd-data)

  4. python evaluate.py det gt_bdd_val.json ../results/bdd_results.json

You will get:

AP : 9.45 (bike)
AP : 40.28 (bus)
AP : 40.56 (car)
AP : 8.66 (motor)
AP : 16.85 (person)
AP : 10.59 (rider)
AP : 7.91 (traffic light)
AP : 23.15 (traffic sign)
AP : 0.00 (train)
AP : 40.28 (truck)
[9.448295420802772, 40.28022967768842, 40.562338308273596, 8.658317480713093, 16.85103955706777, 10.588396343004272, 7.914563796458698, 23.147189144825003, 0.0, 40.27786994583501] 

9.45 40.28 40.56 8.66 16.85 10.59 7.91 23.15 0.00 40.28

mAP 19.77 (512 x 512 input resolution)

If you want to get the mAP for BDD test set,

  1. make
  2. Change the list file in cfg file ("val_bdd_list.txt" --> "test_bdd_list.txt" in "cfg/BDD.data")
  3. ./darknet detector valid cfg/BDD.data cfg/Gaussian_yolov3_BDD.cfg Gaussian_yolov3_BDD.weights
  4. Upload result file ("results/bdd_results.json") on BDD evaluation server Link

On the BDD test set, we got 19.2 mAP (512 x 512 input resolution).

Third-party implementations

Contact

For questions about our paper or code, please contact Jiwoong Choi.

[email protected]




鲜花

握手

雷人

路过

鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

专题导读
热门推荐
阅读排行榜

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服(服务时间 9:00~18:00)

在线QQ客服
地址:深圳市南山区西丽大学城创智工业园
电邮:jeky_zhao#qq.com
移动电话:139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap