The format to submit Track 2 reference features

@dd-mike Hi, what is the format to submit the reference features of Track 2? It is similar to the given

with h5py.File(out, "w") as f:
    f.create_dataset("query", data=M_query)
    f.create_dataset("reference", data=M_ref)
    f.create_dataset('query_ids', data=qry_ids)
    f.create_dataset('reference_ids', data=ref_ids)

Hi @wenhaowang. Yes, that looks about right. Did you still have a question about this? I see that your team was able to make a valid submission to Track 2.

Thanks. I still have a question.
I mean: For phase2, you say we should submit the reference features before 10.19. Therefore, at that time, we do not have query images. Whether we should only submit

with h5py.File(out, "w") as f:
    f.create_dataset("reference", data=M_ref)
    f.create_dataset('reference_ids', data=ref_ids)

instead of

with h5py.File(out, "w") as f:
    f.create_dataset("query", data=M_query)
    f.create_dataset("reference", data=M_ref)
    f.create_dataset('query_ids', data=qry_ids)
    f.create_dataset('reference_ids', data=ref_ids)

?

Hi @wenhaowang. Good question. Please submit the final version of the same file you’ve been submitting in Phase 1.

This is an HDF5 file in the submission format described here, containing your final version of the reference descriptors. This will be the finalized Phase 1 version of the file that you’ve already been submitting for evaluation.

As you point out, you will not yet have the Phase 2 query images. The query descriptors for this submission will be for the Phase 1 query images.

Hope this helps!

It helps a lot. Thanks for your immediate reply.