Coder Social home page Coder Social logo

pe-yolo's People

Contributors

xiangchenyin 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

pe-yolo's Issues

PENet中的bug

image
源代码是注释掉的部分,不加.detach()会报错,请问要不要加呢

代码开发

作者您好,请问什么时候您能够开源整个的项目文件呢?

CUDA out of memory

Hello, thanks for your open source code, what device did you use to run this code? Even on a Tesla V100(32GB) I still encounter this problem, I guess the PENet is the culprit, I have no idea whether PENet was set requires_grad = False in training.

DPM和LEF两个模块

只将DPM和LEF两个模块放到FPN的1×1卷积后,检测到的目标框一直为0,去掉后可正常检测,请问这是什么原因呢

when?

No Procrastination,hhhhhh

导入的问题

请问PENet.py文件里的from ...bulider import BaseModule这里的...builder是指代哪里的文件路径

DataSet

hello, I have downloaded several versions of the datasets without labels,
can you share the dataset, thank you

The visualization problem of image enhancement module

Can you provide the code for visualization when the image is enhanced? I tried to capture the output of the image enhancement module during the model inference process and save it, but the result looked very strange. I hope to get your help, thanks!

PENet.py文件中的小bug

感谢您能开源代码。我在PENet.py文件中发现一个小bug。根据论文中公式(4),Sobel的结果应该经过一个卷积层F3再与输入x相加。所以我认为在文件PENet.py中第209行应该将Sobel结果s_x传入卷积层conv_edge。原先的代码中似乎并没有引入Sobel的计算结果。不知道是我的理解有误还是这的确是一个bug。期待您的回复。

不涨点反而降点

我将PENet加到了yolov7的第一层训练了300epoch,数据集用的Exdark,与未加PENet的yolov7相比,降了8%。请问是为什么呢,数据集划分为6:2:2

数据集划分问题

我将数据集划分为8:2 ,无法在yolov3上复习76.4的map,我怀疑是数据集划分的问题,能否提供一下数据集划分的标签文件

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.