ziplab/HVT

[ICCV 2021] Official implementation of "Scalable Vision Transformers with Hierarchical Pooling"

36
/ 100
Emerging

This project offers a method for image classification that processes visual data more efficiently. It takes in raw images and outputs classifications (e.g., "dog" or "cat") while using less computational power than standard approaches. Data scientists and machine learning engineers working on computer vision tasks would find this useful for training models.

No commits in the last 6 months.

Use this if you need to train image classification models more efficiently, especially with large datasets like ImageNet, and are familiar with PyTorch.

Not ideal if you are looking for a pre-trained model for immediate use without needing to train or fine-tune it yourself.

image-classification computer-vision-training deep-learning-optimization visual-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

33

Forks

5

Language

Python

License

Apache-2.0

Last pushed

Dec 30, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ziplab/HVT"

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