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

How do I run the TartanAir dataset? #9

Open
ztonege opened this issue Nov 27, 2022 · 1 comment
Open

How do I run the TartanAir dataset? #9

ztonege opened this issue Nov 27, 2022 · 1 comment

Comments

@ztonege
Copy link

ztonege commented Nov 27, 2022

Hi,

I believe that this work is trained on the tartanair dataset. However, how do I test tartanvo on tartanair properly?
I tried running it on the abandonedfactory/Easy/P000 from tartanair using this command:

python vo_trajectory_from_folder.py --model-name tartanvo_1914.pkl --kitti --batch-size 10 --worker-num 32 --test-dir /data/tartanair/abandonedfactory/abandonedfactory/Easy/P000/image_left --pose-file /data/tartanair/abandonedfactory/abandonedfactory/Easy/P000/pose_left.txt

This is the result I got:
image

I am using the pre-trained model tartanvo_1914.pkl to test, which I assumed would have good performance since this sequence is in the training set.
Did I do anything wrong? Thanks!

@MarkChenYutian
Copy link
Member

MarkChenYutian commented May 23, 2023

Try remove the argument --kitti. KITTI and TartanAir has very different camera intrinsic parameters.

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