Skip to content
This repository has been archived by the owner on Mar 21, 2024. It is now read-only.

Need help!!!very bad performance with hmdb51 dataset!!! #185

Open
XinPeiHou opened this issue Sep 22, 2021 · 4 comments
Open

Comments

@XinPeiHou
Copy link

Hallo echen~~~, many thanks for this great project in Advance.

When I tried this project with hmdb51 dataset, it shows very bad performance!!!I followed this tutorial in the readme step by step, the accuracy stepped to 100% both in train and valid very immediately. When I checked with run_custom_classifier.py , the results would be that it showed A when my body even did very tiny movement, so B appears quite rarely.

@xiangwentao666
Copy link

When I tried this project with hmdb51 dataset, it shows very bad performance!

Hi, I'm new to this project, but I do not have the weights and I am unable to visit the site provided for downloading weights. Could you please share the weights with me? Thank you very much!

@aureosun
Copy link

aureosun commented Sep 7, 2022

@XinPeiHou @xiangwentao666 did you ever got the demo running? I tried but failed, I do not have the weights, any help or hint,thanks.

@xiangwentao666
Copy link

@XinPeiHou @xiangwentao666 did you ever got the demo running? I tried but failed, I do not have the weights, any help or hint,thanks.

So sorry...... No progress yet......

@chentiop
Copy link

哈喽echen~~~,非常感谢Advance的这个伟大的项目。

哈喽echen~~~,非常感谢Advance的这个伟大的项目。

当我使用 hmdb51 数据集尝试这个项目时,它显示出非常糟糕的性能!!我按照自述文件中的本教程一步一步地操作,准确率立即达到 100%,并且非常有效。当我用 run_custom_classifier.py 检查时,结果是当我的身体甚至做了非常微小的运动时,它显示了 A,所以 B 很少出现。

请问有权重吗,可以分享一份吗谢谢

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants