Zindi
CompeteJobsLearnChatLeaderboardFor Organisations
PartnersMeet the teamPressCase studiesAI4EAC
Primary competition visual

Microsoft Rice Disease Classification Challenge

Helping Egypt
$3 000 USD
Completed (~4 years ago)
Classification
Computer Vision
936 joined
260 active
InfoDataChatLeaderboard
Starti
13 May 22
Closei
14 Aug 22
Reveali
14 Aug 22
User avatar
Koleshjr
Multimedia university of kenya
How are you guys getting scores below 0.10?
Help Ā· 16 Jul 2022, 11:06 Ā· 9

I don't know if i am missing something but i have a good local score of less than 0.10 but a bad lb?

Discussion 9 answers
User avatar
DoubleAgentAmbassador
Zindi Ambassador
16 Jul 2022, 11:13

Local cross validation score of less than 0.1?!

Upvotes 1
User avatar
Koleshjr
16 Jul 2022, 11:47replied to DoubleAgent

yes whats yours?

Upvotes 0
User avatar
DoubleAgentAmbassador
Zindi Ambassador
16 Jul 2022, 15:44replied to Koleshjr

For my current lb score, I have a mean CV score of ~0.094 and yours?!

Upvotes 0
User avatar
DJOE
16 Jul 2022, 11:46

Trust your cv dont give attention to the leader board.

Upvotes 2
User avatar
Koleshjr
16 Jul 2022, 11:47replied to DJOE

Thank you

Upvotes 1
User avatar
Koleshjr
16 Jul 2022, 16:36

0.07 but i am not using folds cv, im using fastai stratified splitter that behaves like train_test_split

Upvotes 1
User avatar
DJOE
17 Jul 2022, 00:34replied to Koleshjr

I use stratifiedkfold cv with 5 folds. cv 0.10 and lb 0.091.

Try also test time augmentation, it improves results.

Upvotes 1
User avatar
Koleshjr
17 Jul 2022, 07:32replied to DJOE

Thank you

Upvotes 0
User avatar
rockerritesh
29 Jul 2022, 18:22

It's painfull!!

Upvotes 0

Join the largest network for
data scientists and AI builders

AboutFAQsPrivacy PolicyTerms of UseRules
Status
Ā© Zindi 2026