leaderj1001/BottleneckTransformers

Bottleneck Transformers for Visual Recognition

47
/ 100
Emerging

This project helps machine learning engineers improve the accuracy of their visual recognition models. It takes standard image datasets and outputs a more precise classification model. This is for professionals building and deploying computer vision systems, such as those in autonomous vehicles, medical imaging, or security.

279 stars. No commits in the last 6 months.

Use this if you are developing computer vision models and want to enhance classification accuracy, especially when working with convolutional neural networks like ResNet.

Not ideal if you are not working with visual data or are looking for a simple, out-of-the-box solution without model fine-tuning.

computer-vision image-classification deep-learning model-optimization visual-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

279

Forks

49

Language

Python

License

MIT

Last pushed

Mar 14, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/leaderj1001/BottleneckTransformers"

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