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

Understanding 'olsson' dataset #351

Closed
Padarn opened this issue Oct 14, 2021 · 5 comments
Closed

Understanding 'olsson' dataset #351

Padarn opened this issue Oct 14, 2021 · 5 comments

Comments

@Padarn
Copy link

Padarn commented Oct 14, 2021

I'm trying to run gtsfm, but the README seems out of date, the command

python gtsfm/runner/run_scene_optimizer.py --config_name {CONFIG_NAME} --dataset_root {DATASET_ROOT} --image_extension jpg --num_workers {NUM_WORKERS}

can no longer work, as the gtsfm/runner/run_scene_optimizer.py has been removed.

I tried to instead use

gtsfm/runner/run_scene_optimizer_olssonloader.py --config_name {CONFIG_NAME} --dataset_root {DATASET_ROOT} --image_extension jpg --num_workers {NUM_WORKERS}

but I don't fully understand the format of the dataset expected, currently, I get an error

raise ValueError(f"No intrinsics found for index {index}.")

Are there any docs on how the data should be structured in the dataset_root?

(also, related, do intrinsics need to be specified, or can they be inferred?

@ayushbaid
Copy link
Contributor

Thanks for raising this issue. You are right that run_scene_optimizer.py has been removed. Instead of defaulting to the format of Olsson dataset, we will prioritize working on a simple runner where you specify the folder with the images and can run SfM on it.

We will pick up this task as top priority and will provide a solution within a couple of days.

@ayushbaid
Copy link
Contributor

Resolution tracked in #352

@Padarn
Copy link
Author

Padarn commented Oct 14, 2021

Thanks a lot. Happy to help out if there is some documentation on the format I can follow.

@johnwlambert
Copy link
Collaborator

Hi @Padarn, thanks for your interest in our work. Suppose you have a folder of images, all you need to do is create a structure like

└── DATASET_ROOT
       ├── images
               ├── image1.jpg
               ├── image2.jpg
               ├── image3.jpg

and run

python gtsfm/runner/run_scene_optimizer_olssonloader.py --dataset_root /path/to/DATASET_ROOT --image_extension jpg --config_name deep_front_end.yaml --num_workers 4

(or however many workers you desire).

Currently we require EXIF data embedded into your images (or you can provide ground truth intrinsics in the expected format for an Olsson dataset, or COLMAP-exported text data, etc)

@johnwlambert
Copy link
Collaborator

Can you double check that your data has EXIF data embedded?

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

3 participants