huawei-noah/Efficient-AI-Backbones
Efficient AI backbone models for computer vision including GhostNet, Vision Transformers (TNT), and ViG developed by Huawei Noah's Ark Lab.
Not currently ranked — collecting fresh signals.
star history
This repository provides implementations of efficient neural network architectures for computer vision. It includes GhostNet and GhostNetV2 (model compression via cheap operations), TNT (Transformer in Transformer for vision), WaveMLP (MLP-based architecture), and ViG (Vision Graph Neural Network). Models are available in both PyTorch and MindSpore frameworks, with pretrained weights for image classification tasks.
Frequently asked
- What is huawei-noah/Efficient-AI-Backbones?
- Efficient AI backbone models for computer vision including GhostNet, Vision Transformers (TNT), and ViG developed by Huawei Noah's Ark Lab.
- Is Efficient-AI-Backbones open source?
- Yes — huawei-noah/Efficient-AI-Backbones is an open-source project tracked on heatdrop.
- What language is Efficient-AI-Backbones written in?
- huawei-noah/Efficient-AI-Backbones is primarily written in Python.
- How popular is Efficient-AI-Backbones?
- huawei-noah/Efficient-AI-Backbones has 4.4k stars on GitHub.
- Where can I find Efficient-AI-Backbones?
- huawei-noah/Efficient-AI-Backbones is on GitHub at https://github.com/huawei-noah/Efficient-AI-Backbones.