Hello @vchung
for the final submission, where I can see the result?
Created by Lorenzo de Trizio Lorenzo.deTrizio Here is an example https://github.com/Sage-Bionetworks-Challenges/sample-model-templates/blob/main/python/run_model.py. Hopefully, it is helpful! Dear @gaia.sage,
Can you share an example of code to read the real validation data in the Docker file?
Thank you for your help.
Thanks @gaia.sage ! Ciao @Lorenzo.deTrizio, the actual data cannot be downloaded due to its sensitivity. Essentially, once you submit your model, it will use the real data to make predictions. The file names for the real data are the same as the synthetic data but without the "_val_synthetic" in the name. I hope this helps!
Please don't hesitate to ask if you have any more questions. Hello @gaia.sage
thanks for reply :)
Yes the prediction use the synthetic data.
Where I can download the real data?
Thanks in advance
Lorenzo Hello @Lorenzo.deTrizio,
The discrepancies in IDs occur because the Docker container's prediction is using the IDs of the synthetic data. To help us understand better, could you confirm whether your model is making predictions on the real data once it's submitted?
Thanks,
Gaia @vchung Hello,
pls help us for this enquiry.
Thanks in advance,
Lorenzo Hello, I have received the submission result:
'Evaluation failed for Submission 9748297.
Reason: 'Found 3060 missing ID(s): ['10003643', '10004008', '10007435', '10046893', '10052504', '10055911', '10066586', '10082511', '10092744', '10103044', '10143911', '10155246', '10160793', '10162140', '10177776', '10178211', '10181886', '10192776', '10193661', '10194481', '10203009', '10207092', '10217473', '10235033', '10241240', '10278717', '10285122', '10330872', '10349237', '10351428', '10360471', '10374199', '10388184', '10419167', '10428067', '10432757', '10433457', '10433534', '10448793', '...'.
Please contact the organizers for more information. '
But if I search the ID into prediction.csv, this value don't exist. Again: we wrongs somethings?