Primary competition visual

Wadhwani AI Bollworm Classification Challenge by #ZindiWeekendz

Helping India
$300 USD
Challenge completed ~3 years ago
Classification
Computer Vision
88 joined
39 active
Starti
Oct 07, 22
Closei
Oct 10, 22
Reveali
Oct 10, 22
About

Data has been collected from farmers since 2018. Some of that data was collected using a dedicated data collection app. Most of it, however, was collected from the app itself; making the dataset unique among other farm pest datasets. There are approximately 13 000 images.

Positive images are indicated by a 1 in the training set. These are images that contain at least one bollworm on an insect card. Negative images are images that do not have a bounding box and cannot be used to count the number of bollworms per card.

The objective of this competition is to create a machine learning model that classifies images as positive or negative. This model will form one part of the greater solution to control bollworm pests in India delivered by the Wadhwani AI app.

This is a negative image.

This is a postive image with 6 pink bollworm and 6 American bollworm.

Files
Description
Files
This shows the submission format for this competition, with the ‘Image_id’ column mirroring that of Test.csv and the ‘Label’ column containing your predictions. The order of the rows does not matter, but the names of the ‘Image_id’ must be correct.
These are the IDs of the images you will use to test your model.
These are the IDs of the images you will use to train your model.
This file is ~6 GB, you will use these images to build your model.
This is a starter notebook to help you make your first submission. If the file open weirdly you can ctrl-S and it will save to your download folder.