Andrewwango/open-set-resnet

Open set classification of car models. This 3-step classifier solves the problem where dogs are classified as cars, by first filtering these images out using ResNet CNNs transfer-trained on different datasets.

28
/ 100
Experimental

This tool helps improve image classification systems by filtering out irrelevant images before they are miscategorized. It takes an image as input and determines if it belongs to a predefined set of categories, like specific car models, or if it's an unrelated object. This is useful for anyone working with image datasets where accurate identification is crucial and misclassifying 'unknown' items is a problem.

No commits in the last 6 months.

Use this if your image classifier frequently mislabels images that are completely outside its intended categories, such as identifying a dog as a car model.

Not ideal if you need to classify images where the 'unknown' items are very similar to your target categories, as it focuses on filtering broadly irrelevant inputs.

image-recognition quality-control data-preprocessing computer-vision content-moderation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

12

Forks

4

Language

Jupyter Notebook

License

Last pushed

Feb 04, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Andrewwango/open-set-resnet"

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