KentaItakura/Data-Augmentation-using-Mix-up-with-Custom-Training-Loop-with-MATLAB

Data Augmentation using Mix-up with Custom Training Loop

20
/ 100
Experimental

This project helps image recognition practitioners improve the accuracy of their classification models, especially when they have limited training data. It takes existing image datasets and generates new, synthetic training images by blending pairs of existing images. The output is a more robust image classification model ready for deployment, used by scientists, engineers, or anyone working with image data in MATLAB.

No commits in the last 6 months.

Use this if you are a deep learning practitioner using MATLAB for image classification and want to improve model performance by expanding your training dataset through a technique called 'mix-up' data augmentation.

Not ideal if you are not working with image classification tasks, do not use MATLAB for your deep learning projects, or are looking for data augmentation methods other than mix-up.

image-classification deep-learning computer-vision data-augmentation MATLAB
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

MATLAB

License

BSD-3-Clause

Last pushed

Jan 26, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KentaItakura/Data-Augmentation-using-Mix-up-with-Custom-Training-Loop-with-MATLAB"

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