icolbert/upsampling

Algorithmic solutions to optimize inference for convolution-based image upsampling. Coded for clarity, not speed.

34
/ 100
Emerging

This project helps optimize the process of increasing image resolution using deep learning. It takes in trained image upsampling models and converts their internal workings to perform the same task more efficiently. This is designed for engineers or researchers deploying image processing systems on devices with limited memory or power.

No commits in the last 6 months.

Use this if you need to run high-quality image upsampling models on resource-constrained devices like embedded systems or edge computing platforms.

Not ideal if your primary concern is the absolute fastest training time or if you have ample computational resources for inference.

edge-computing image-processing computer-vision embedded-systems device-optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

10

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 26, 2022

Commits (30d)

0

Get this data via API

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

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