How are algorithm results provided to the evaluation container?¶

An evaluation is run after all the algorithm jobs for a submission have finished successfully. The outputs produced by the algorithm are then collected and provided to the evaluation container at the following path: /input/{job_pk}/output/{socket_relative_path}, where

• job_pk is the primary key (pk) of each algorithm job
• socket_relative_path is the relative_path for each of the output sockets. The relative path's for each socket can be found here.

The outputs of the algorithm jobs are inputs for the evaluation container.

If the algorithms output a ct-image and a nodule-locations json file, you would read the corresponding files for the first algorithm job from /input/{job_pk}/output/images/ct/ and /input/{job_pk}/output/nodule-locations.json

To match the algorithm jobs' output with the original input filenames, see:
If the generated outputs from an algorithm do not have the same name / UUID as the corresponding inputs, how do I match them to the ground truth?