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

monodepth2 added ARN #94

Open
Be997398715 opened this issue Jan 16, 2022 · 2 comments
Open

monodepth2 added ARN #94

Be997398715 opened this issue Jan 16, 2022 · 2 comments

Comments

@Be997398715
Copy link

Thank you for your great project. I try to train monodepth2 with ARN module for tum dataset(most of sequences, every sequence for per 5 frame sampling, hw=640480, mono train mode with gt_depth), and I find the old monodepth2 could not handle this dataset well, cause every step the loss is 0, while monodepth2 with ARN could work a litter(loss could drop from 0.2 to 0.05 by ARN module loss funtion), where should I pay attention to when add ARN to monodepth2 as a seperate module in mono train mode?

@JiawangBian
Copy link
Owner

I didn't try it directly on the monodepth2 framework. I suggest that you use our PyTorch lightning re-implementation https://github.com/JiawangBian/sc_depth_pl, where we have added the features of monodepth2 (minimum loss, auto-mask) into our baseline.

@Be997398715
Copy link
Author

so sc_depth_pl includes all features in monodepth2 right? I will try later, thanks for your reply:)

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