suous/RecNeXt
RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations
This project offers a new way to process visual information efficiently, especially useful for computer vision engineers and mobile app developers working with image analysis. It takes raw image data and produces optimized visual feature representations that can improve the performance of tasks like object detection or image classification on devices with limited resources, such as smartphones.
No commits in the last 6 months.
Use this if you are building computer vision applications for mobile devices and need highly accurate image recognition or object detection while keeping resource usage low.
Not ideal if your primary goal is to train large-scale, high-performance models on powerful servers without resource constraints.
Stars
19
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/suous/RecNeXt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...