sacmehta/ESPNetv2

A light-weight, power efficient, and general purpose convolutional neural network

47
/ 100
Emerging

This project offers a lightweight and power-efficient convolutional neural network, ESPNetv2, designed for image analysis tasks. It takes raw image data as input and can output classifications (like identifying objects in an image) or detailed semantic segmentations (like outlining different elements within an image, such as roads, cars, or pedestrians). This is ideal for developers and researchers building applications that require real-time image processing on devices with limited power, such as mobile phones or embedded systems.

454 stars. No commits in the last 6 months.

Use this if you are a developer or researcher building computer vision applications and need a highly efficient neural network model for image classification or semantic segmentation that consumes minimal power and runs effectively on edge devices.

Not ideal if you are looking for an out-of-the-box application for end-users, or if you require a solution that is actively maintained and regularly updated in this specific repository.

computer-vision image-segmentation object-classification edge-computing real-time-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

454

Forks

73

Language

Python

License

MIT

Last pushed

Jan 29, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sacmehta/ESPNetv2"

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