Comments (10)
Sorry for this bug. I've updated the yolo.py, please download new source code.
from cst-yolo.
Sorry for this bug. I've updated the yolo.py, please download new source code.
Hello author, may I ask if the superiority of your network over the source network yolov7 is only shown in big data? Because when I trained in the data set with only 90 pictures, the result was much worse than that of yolov7 (yolov7's F1 is 0.75, while the author's F1 of your network is 0.43)
from cst-yolo.
Sorry for this bug. I've updated the yolo.py, please download new source code.
Hello author, may I ask if the superiority of your network over the source network yolov7 is only shown in big data? Because when I trained in the data set with only 90 pictures, the result was much worse than that of yolov7 (yolov7's F1 is 0.75, while the author's F1 of your network is 0.43)
Thank you for testing our model CST-YOLO. The evaluation metrics of the object detection task are mAP, AP50:95, etc. We don't consider F1 as an evaluation metric.
from cst-yolo.
Using the author's updated code to train in my data set, the training results of the author's proposed network are indeed worse than those of the source network yolov7, including the [email protected] result mentioned by the author
from cst-yolo.
Using the author's updated code to train in my data set, the training results of the author's proposed network are indeed worse than those of the source network yolov7, including the [email protected] result mentioned by the author
Which dataset did you use? Does your dataset include small objects? What is your running environment?
from cst-yolo.
from cst-yolo.
自己制作的数据集,主要是小对象,运行环境与yolov7一致。
…
------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2023年7月20日(星期四) 晚上10:18 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [mkang315/CST-YOLO] When I execute train.py I get the following error: NameError: nane 'myModel' is not defined (Issue #1) @.***作者提到的结果 您使用的是哪个数据集?您的数据集包括小对象吗?你的运行环境是怎样的? — 直接回复此邮件,在GitHub上查看,或者取消订阅. @.***与>.
Is your dataset publicly available? Or you could send it to me. CST-YOLO aims to blood cell detection. It isn't very strange that the performance of CST-YOLO is worse than YOLOv7 on other datasets. Also, our running environments are different from yours.
from cst-yolo.
from cst-yolo.
抱歉,数据集还没公开,但是你可以尝试一下,邮件发给你,注意查收,你可以试试,然后麻烦你告诉我结果
…
------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2023年7月20日(星期四) 晚上10:27 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [mkang315/CST-YOLO] When I execute train.py I get the following error: NameError: nane 'myModel' is not defined (Issue #1) 自己制作的数据集,主要是小对象,运行环境与yolov7一致。 … ------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2023年7月20日(星期四) 晚上10:18 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [mkang315/CST-YOLO] When I execute train.py I get the following error: NameError: nane 'myModel' is not defined (Issue #1) @.***作者提到的结果 您使用的是哪个数据集?您的数据集包括小对象吗?你的运行环境是怎样的? — 直接回复此邮件,在GitHub上查看,或者取消订阅. @.与>. Is your dataset publicly available? Or you could send it to me. CST-YOLO aims to blood cell detection. It isn't very strange that the performance of CST-YOLO is worse than YOLOv7 on other datasets. Also, our running environments are different from yours. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.>
Please send the download link (e.g. pan.baidu.com) to *@.com. Is the dataset annotated manually? Have you divided the train and test sets? I'll evaluate CST-YOLO and YOLOv7 and find the reason why not effective on your dataset.
from cst-yolo.
from cst-yolo.
Related Issues (2)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from cst-yolo.