Primary competition visual

Classification for Landslide Detection by ITU

1 000 CHF
Completed (~1 year ago)
Classification
Earth Observation
Python
GIS
Computer Vision
Machine Learning
Deep Learning
1028 joined
303 active
Starti
17 Apr 25
Closei
04 Aug 25
Reveali
04 Aug 25
Evaluation Always Returns 0.000 — with SampleSubmission.csv
28 Jul 2025, 19:20 · 2

Hello Zindi Team,

Please I need your input/ recommendations on this.

All my submissions returns a score of 0.000 — when i submitted the official SampleSubmission.csv. A file with all label between 0 and 1 (all int). Could you please confirm whether the evaluation pipeline is functioning correctly? Thank you,

Discussion 2 answers
User avatar
crossentropy

I think the submission file has all 0's, it only makes sense that the score is 0

When computing F1, recall is taken into consideration, and since there are no 1's in the sample submission, all true positives are missed, thus automatically reducing the recall score to 0. So automatically, the F1 will be 0

Upvotes 0
User avatar

Thank you for your response. I totally understand you.

But, on a serious note, some of the sample submission file has 1's (all true positives), but the number of 0's far outweigh the number of 1's.

Upvotes 0