Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

关于两种数据集训练的差异问题 #166

Open
syqisme opened this issue Dec 14, 2023 · 5 comments
Open

关于两种数据集训练的差异问题 #166

syqisme opened this issue Dec 14, 2023 · 5 comments

Comments

@syqisme
Copy link

syqisme commented Dec 14, 2023

您好,最近我在您的项目上进行修改并学习,目前在pascal voc上效果较好,但是在cityscapes数据集上效果很差,目前找了很久没找到原因,于是想问您一下,请问您在训练两种数据集上有什么设置上或者训练策略上需要注意的地方呢?目前我看到了一些config文件内的细小差别,可是怎么尝试效果都一般,如果能回复并给我一些建议的话,我将非常感谢!

@Haochen-Wang409
Copy link
Owner

请您按照这个 config 进行 Cityscapes 的实验:https://github.com/Haochen-Wang409/U2PL/blob/main/experiments/cityscapes/744/ours/config.yaml

@syqisme
Copy link
Author

syqisme commented Dec 20, 2023

请您按照这个 config 进行 Cityscapes 的实验:https://github.com/Haochen-Wang409/U2PL/blob/main/experiments/cityscapes/744/ours/config.yaml

十分感谢您的回复,我按照这个去进行尝试,得到结果再来告诉您

@lukasingle
Copy link

What is the reason for a single card training error in the windows system
question

@Haochen-Wang409
Copy link
Owner

This code does not support training on a single GPU.

@79zzz
Copy link

79zzz commented Sep 1, 2024

local_rank = int(os.environ["LOCAL_RANK"])将local_rank设置成0试试

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

No branches or pull requests

4 participants