Primary competition visual

Classification for Landslide Detection by ITU

1 000 CHF
Completed (10 months ago)
Classification
Earth Observation
Python
GIS
Computer Vision
Machine Learning
Deep Learning
1006 joined
303 active
Starti
Apr 17, 25
Closei
Aug 04, 25
Reveali
Aug 04, 25
CV vs LB!
Help · 31 May 2025, 20:24 · 10

It's good sign if both has relative correclation.

let's share both score.

my score:

cv to lb

0.85 :::: 0.875,

0.86 :::: 0.865

0.87 :::: 0.851

Discussion 10 answers
User avatar
crossentropy
Federal university of Technology, Akure

cv to lb

0.83x :::: 0.82x

May i ask what your local train f1 is?

I think I(we) might be overfitting?

8 Jun 2025, 17:59
Upvotes 1

I did't f1 metric use for training samples instead log_loss, that is 0.08

User avatar
crossentropy
Federal university of Technology, Akure

ok

thanks

CV to LB

0.90xx ::::::0.81xx

while my train f1 is 0.95xx

8 Jun 2025, 23:43
Upvotes 0
User avatar
nymfree

CV = 0.8196 | LB = 0.803970223

What model are you using? NN or GBDT?

20 Jun 2025, 21:50
Upvotes 0
User avatar
CodeJoe

I am using GBDT. Mine is 0.8583, lb = 0.8512.

User avatar
CodeJoe

@nymfree are you using a cv approach?

User avatar
nymfree

Yes I am using a cv-like approach - just a bunch of 2d convs so far.

User avatar
CodeJoe

Alright, I will switch to a cv approach soon.