Giter VIP home page Giter VIP logo

ow-yolo's Introduction

015

快速开始

1. 安装

同yolov5

2. 推理

推理示例
$ python detect.py --source data/images --weights m-obj365.pt --unknownconf 0.45 --conf 0.25 
$ python detect.py --source data/images --weights s-coco.pt --unknownconf 0.25 --conf 0.25
'''
参数解读
unknownconf: 当网络预测的“不知道”分数大于此阈值时预测为不知道,否则输出已知分类。
1)与已知类精度关系:当已知类精度越高时,“不知道”在已知类上发生的情况将越少,预测未知类时可以设定更低的unknownconf而不影响已知类性能。
2)与训练集大小关系:训练集越丰富,预测未知类的能力越强
注:可根据需求调节此参数,需要注意的是由于资源问题,在objects365数据集下训练的模型m-obj365.pt仅在小模型下训练了30轮,精度较低,建议采用较高阈值。
其他参数:
1)非极大值抑制:默认类内NMS(非极大值抑制)iou阈值为0.45,参数为iou;同时进行类间NMS,iou阈值为0.75,后续将提供参数接口。
2)不知道的物体类名:可在detect文件中修改,后续将提供接口。             
'''
视频展示
  1. demo1
  2. demo2

3. 预训练模型

s-coco.pt
m-obj365.pt

coco数据集性能

Model size
(pixels)
mAPval
0.5:0.95
mAPval
0.5
yolov8-n 640 37.3 52.6
OW-yolov8-n 640 37.9 (only known 38) 53.7 (only known 53.9)
OW-yolov8-n-la 640
la : label attention

4. 后续功能

图像分类、实例分割

ow-yolo's People

Contributors

buxihuo avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

ow-yolo's Issues

Would this be able to detect true "unseen unknowns"?

I've seen many open-set object detection projects that can detect "seen unknowns" (classes that are already present, although unlabeled, in the training pipeline).

But I'm looking to detect "unseen unknowns" (classes that do not exist in the image space of the dataset at all). Is this project capable of doing this, at least to certain capability?

1 楼

这里什么也没有

训练模型识别未知的负样本

你好我想问一下,添加未知类分数训练模型区分已知未知时,是否有负样本的参与,即手动标注的未知对象。如果没有又是如何训练模型在已知类上的未知分数趋近于0。

IndexError: list index out of range

使用您提供的预训练权重预测会出现

IndexError: list index out of range

请问:

  1. 所提供的权重是基于coco还是voc训练的?
  2. 是否可以提供下与权重相搭配的yaml配置文件?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.