ndb796/Small-ImageNet-Validation-Dataset-1000-Classes

This is a subset of the ImageNet validation dataset. This dataset has 5 images per class.

29
/ 100
Experimental

This dataset offers a smaller, more manageable collection of images for testing your image classification models. You provide your trained model, and this dataset provides 5 representative images for each of ImageNet's 1000 classes, allowing you to quickly evaluate how well your model identifies a wide variety of objects and scenes. It's designed for machine learning practitioners and researchers who need to efficiently check their model's performance on a diverse set of images.

No commits in the last 6 months.

Use this if you need a quick and efficient way to validate the performance of your image classification model against a diverse set of categories without downloading the entire large ImageNet validation dataset.

Not ideal if you require a comprehensive, high-volume evaluation of your model's robustness or want to fine-tune your model on a large validation set.

image-classification model-validation computer-vision machine-learning-research dataset-subsetting
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

10

Forks

7

Language

Jupyter Notebook

License

Last pushed

Mar 05, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ndb796/Small-ImageNet-Validation-Dataset-1000-Classes"

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