JunlinHan/CropMix

Code of CropMix: Sampling a Rich Input Distribution via Multi-Scale Cropping

23
/ 100
Experimental

This tool helps machine learning engineers and researchers improve the training of computer vision models. It takes your existing image datasets and applies a multi-scale cropping technique to create richer, more diverse input images. This process leads to better-performing models for tasks like image classification, contrastive learning, and masked image modeling.

No commits in the last 6 months.

Use this if you are training computer vision models and want to enhance their accuracy and robustness by providing more varied and informative training data.

Not ideal if you are working with non-image data or if your existing data augmentation strategies are already sufficient for your specific vision task.

computer-vision machine-learning-training image-classification data-augmentation model-performance
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

17

Forks

2

Language

Jupyter Notebook

License

Last pushed

Oct 08, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JunlinHan/CropMix"

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