mmaaz60/EdgeNeXt
[CADL'22, ECCVW] Official repository of paper titled "EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications".
This project offers pre-trained models for computer vision tasks that run efficiently on mobile or edge devices. It takes in images and outputs classifications, object detections, or segmentation masks. This is designed for AI/ML engineers and researchers who need to deploy high-performing computer vision models on resource-constrained hardware.
411 stars. No commits in the last 6 months.
Use this if you need to build and deploy accurate image classification, object detection, or image segmentation models on devices like smartphones, drones, or IoT cameras.
Not ideal if your application runs on powerful servers with ample computational resources, where the focus is solely on maximum accuracy regardless of efficiency.
Stars
411
Forks
45
Language
Python
License
MIT
Category
Last pushed
Jul 25, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/mmaaz60/EdgeNeXt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Kohulan/DECIMER-Image_Transformer
DECIMER Image Transformer is a deep-learning-based tool designed for automated recognition of...
sovit-123/vision_transformers
Vision Transformers for image classification, image segmentation, and object detection.
fcakyon/video-transformers
Easiest way of fine-tuning HuggingFace video classification models
leaderj1001/BottleneckTransformers
Bottleneck Transformers for Visual Recognition
qubvel/transformers-notebooks
Inference and fine-tuning examples for vision models from 🤗 Transformers