Standard Bank Tech Impact Challenge: Animal classification
Knowledge
Create a binary classification algorithm to distinguish zebras from elephants
30 August 2019–∞
96 data scientists enrolled, 35 on the leaderboard
What to ssubmit as the final product?
published 14 Nov 2019, 08:01

I don't understand what is required. Or in other words what is supposed to be submitted.

Should I submit the trained model or what?

For each image in the test set, you're submitting a prediction. So you'll submit a CSV file with two columns - one for the image ID and the other with a prediction between 0 (Zebra) and 1 (Elephant). You can submit probabilities since the scoring metric is log-loss. So for example, for image ID ASG001af81_2 my model predicted 93% chance of it being an elephant, so my submission's first row after the column headings was 'ASG001af81_2, 0.93452066'. See the sample submission file for what your submission should look like.