Hi,
It may be a silly thing to ask, but I am unable to relate the detailed results with Image Ids in Valid dataset. e.g. If I would I like to know how well my current algorithm predicts for image with ID "15516_sat.jpg" then what I need to do or how to map with detailed results?
Thanks
Posted by: anil2185 @ April 23, 2018, 12:23 p.m.anil2185:
We intentionally obfuscate the output filenames so that the participants don't try to overfit the model to specific validation/testing images/dataset, and also lowering down the probability of cheating.
Posted by: jinghuang @ April 23, 2018, 8:10 p.m.