Computer Vision for Image Classification
'%3e%3cg id='b'%3e%3cpath id='a' fill='%23E5BE01' d='M116.1 0 35.692 4.699l76.452 25.35L33.26 13.777l67.286 44.273L28.56 21.915l53.534 60.18-60.18-53.534 36.135 71.985L13.777 33.26l16.272 78.884-25.35-76.452L0 116.1-1-1z'/%3e%3cuse xlink:href='%23a' transform='scale(1 -1)'/%3e%3c/g%3e%3cuse xlink:href='%23b' transform='scale(-1 1)'/%3e%3ccircle r='34.3' fill='%23E5BE01' stroke='%2300A1DE' stroke-width='3.4'/%3e%3c/g%3e%3c/svg%3e)
Helping Rwanda
Knowledge
Active
Classification
Computer Vision
Multi-class Classification
289 joined
46 active
Test set log loss vs submission
Data · 3 May 2019, 08:10 · 1
Interesting. I get a logloss on my test set (supplied) of 0.17 but this translates to a logloss of 0.49 on the submission results. This seems to be a fairly large discrepency and makes it somewhat challenging to find ways to improve the model. Anyone else eperience this large difference?
I have found the same issue in Farm Pin Crop Detection Challenge. For me it is very strange also. Do someone have any explanations and ideas?