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
poppingtonic
Pretraining a self-supervised learning algorithm to solve this challenge (one way to use both image types)
Notebooks Ā· 24 Jul 2022, 13:56 Ā· 2

This repository contains two training notebooks and notes showing how to pretrain from scratch, (or from imagenet weights) a self-supervised encoder that can be finetuned to solve this task. I also experimented with progressive resizing, and have released a pretrained encoder called mwalimu-128 for the 128px image size, that achieves a validation loss of 4.98 for xresnet34, and 4.35 for res2next50. Link is in the README:

https://github.com/poppingtonic/semisupervised-rice-africa

Discussion 2 answers
User avatar
Koleshjr
24 Jul 2022, 18:22

Amazing work. Just a question, how do you do this supervised transform in ImageDataLoaders.from_lists in fastai?

Upvotes 2
User avatar
poppingtonic
26 Jul 2022, 07:53replied to Koleshjr

Thank you @Koleshjr. I'm not sure I understand the question though, which supervised transform are you referring to?

Upvotes 0

Join the largest network for
data scientists and AI builders

AboutFAQsPrivacy PolicyTerms of UseRules
Status
Ā© Zindi 2026