CodaLab platform: To submit your result(s), the competition is held on CodaLab.

The exoplanet imaging data challenge will consist of several stages, each one with its own type of submission and metrics.

Stage 1: Deadline 30st of September 2020

For each algorithm, the participants must submit:

File format: Every file must be in .fits format.

Threshold: The detection threshold is one single value for all of the detection maps submitted. Also the threshold must be a 1x1 array containing the chosen scalar value. If needed, the detection maps can be streched to a common threshold value. We remind that any signal above the threshold value will be considered as a detection.

Submission into a .zip file: All of the .fits files must be submitted within a single .zip file, with a flat structure (e.g. using the command on Mac > zip -r -X -j archive_name.zip folder_to_compress). One .zip file must be submitted for each sub-challenge (one for ADI and one for ADI+mSDI).

Note: Each submission must correspond to the results of applying a single algorithm to all the datasets. If your algorithm works for both 3D and 4D datasets then you need to make two submissions (to have your score on each scoreboard). Please keep in mind that a partial submission for a given sub-challenge is possible, but that will penalize the metrics computations and your score. You can make several submissions, even if only one will show up on the competition webpage leaderboard, all of the submissions will be processed off-line.

Potential error message

Zipping the file: The zip file must be flat (i.e. without subfolder structure), please consider checking this aspect.

Space left on device: This error occurs when a compute worker is full, usually because it has too many docker images. If this happens, we have to contact CodaLab and clean the repository. Please notify us if you encounter such error (exoimg.datachallenge@gmail.com).

Other error message: Please contact us if you encounter any issue when submitting your results exoimg.datachallenge@gmail.com.

Note: Please check out the documentation of the Astropy Python library if you want to know more about saving data in FITS format. Optionally, the VIP Python library contains a wrapper (vip_hci.fits.write_fits()) of Astropy for saving Python numpy arrays as FITS files.

Example, ADI

For example, for submitting your results of the 1st sub-challenge (ADI), you must gather the following files in .zip format (any name can be used):

Optionally, you can include:

Example, ADI+mSDI

For example, for submitting your results of the 2nd sub-challenge (ADI+mSDI), you must gather the following files in .zip format (any name can be used):