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

预测速度问题 #54

Open
gzheng91 opened this issue Dec 6, 2024 · 1 comment
Open

预测速度问题 #54

gzheng91 opened this issue Dec 6, 2024 · 1 comment

Comments

@gzheng91
Copy link

gzheng91 commented Dec 6, 2024

我在A2000的显卡上预测(640480)大概需要100ms,时间点久。你们有尝试将粗匹配特征resize到3040(原来是60*80)嘛.这样是不是应该能够大大预测速度吧,不知道对预测结果影响大不大?你们有做过这方面的测试吗?

@wyf2020
Copy link
Contributor

wyf2020 commented Dec 11, 2024

如果使用1/16的粗特征需要重新训练模型,并且LoFTR的文章中ablation实验也做过这样的实验,会降低模型精度。另一种做法是直接用更小分辨率的图像增加速度,并不需要重新训练模型,但同样的也会降低预测结果的精度,这里有indoor的精度和速度随分辨率变化的测试脚本

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

2 participants