KentaItakura/Image-classification-using-oversampling-imagedatastore

This example shows how to classify images for imbalanced training dataset using oversampling

34
/ 100
Emerging

This project helps anyone training image classification models when they have an imbalanced dataset, meaning some categories have many more images than others. It takes your existing image dataset, which can be unevenly distributed, and balances it by intelligently replicating images in under-represented categories. The output is a trained deep learning model that performs better at classifying images across all categories, even those that were initially scarce.

No commits in the last 6 months.

Use this if you are building an image classification system and your training data has significantly more examples for some classes than others, which can lead to poor performance on the minority classes.

Not ideal if your image datasets are already well-balanced across all classes or if you prefer a down-sampling approach to handle imbalanced data.

image-classification deep-learning-training computer-vision food-recognition imbalanced-data
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

8

Forks

3

Language

MATLAB

License

MIT

Last pushed

Jul 28, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KentaItakura/Image-classification-using-oversampling-imagedatastore"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.