Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

krishnakalyan3/iclr-crop-disease-zindi

Domaine:

agriculture

Type de record:

project
Créateur:
kri
Hôte:
Identify wheat rust in images from Ethiopia and Tanzania # My solution for ICLR Workshop Challenge Identify wheat rust in images from Ethiopia and Tanzania. The competition page can be found here. My Solution - 5 fold cross validation - Mixup - EfficientNet Model trained on resized images 524x524 - One Cycle Policy / Differential Learning rate using learning rate finder - PseudoLabeling My main misktakes - Overfit to the leaderboard - Bad CV stratergy ``` Private Leaderboard rank 19 Ideas should have tested - Normalization Code (mean/std) - TTA - Gradient Clipping - Remove confusing Images - Builind a Widget to explore / remove data from the model - Remove images (hash/phash) ``` Results

Visit

github.com

Tasks

computer visionimage classification

Similaires

ICLR Workshop Challenge #1: CGIAR Computer Vision for Crop DiseaseZindi Ghana crop disease detection datasetArnolFokam/cgiar-zindi-crop-classificationzoom-BT/zindi-chad-crop-yieldICLR Workshop Challenge #2: Radiant Earth Computer Vision for Crop Detection from Satellite ImageryCrop Disease (Ghana)

ICLR Workshop Challenge #1: CGIAR Computer Vision for Crop Disease

Identify wheat rust in images from Ethiopia and Tanzania, and win a trip to present your work at ICLR 2020 in Addis Ababa.
The imagery data comes from a variety of sources. The bulk of the data was collected in-field by CIMMYT and CIMMYT partners in Ethiopi

Zindi Ghana crop disease detection dataset

Competition on zindi- data science

ArnolFokam/cgiar-zindi-crop-classification

Code for challenge https://zindi.africa/competitions/cgiar-crop-damage-classification-challenge # G

zoom-BT/zindi-chad-crop-yield

Winning solution (1st place, private LB) for a Zindi challenge predicting crop yields in Chad from s

ICLR Workshop Challenge #2: Radiant Earth Computer Vision for Crop Detection from Satellite Imagery

Identify crop type using satellite imagery, and win a trip to present your work at ICLR 2020 in Addis Ababa.
The objective of this competition is to create a machine learning model to classify fields by crop type from images collected during the growing sea

Crop Disease (Ghana)

Afrocentric (African) Crop Dataset