murufeng/awesome_lightweight_networks
The implementation of various lightweight networks by using PyTorch. such as：MobileNetV2，MobileNeXt，GhostNet，ParNet，MobileViT、AdderNet，ShuffleNetV1-V2，LCNet，ConvNeXt，etc. ⭐⭐⭐⭐⭐
This project provides pre-built, optimized deep learning models designed for deployment on devices with limited computing power, such as mobile phones or embedded systems. It offers a collection of various lightweight neural network architectures like MobileNetV2, GhostNet, and ShuffleNet, allowing engineers to quickly select and use efficient models for tasks like image classification, detection, and segmentation. The end-user is typically an AI/ML engineer or researcher focused on deploying machine learning models to edge devices.
911 stars. No commits in the last 6 months.
Use this if you need to integrate high-performing yet resource-efficient deep learning models into applications running on mobile or embedded hardware.
Not ideal if your primary goal is to train the most complex, state-of-the-art models without any constraints on computational resources or model size.
Stars
911
Forks
163
Language
Python
License
MIT
Category
Last pushed
May 16, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/murufeng/awesome_lightweight_networks"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
InterDigitalInc/CompressAI
A PyTorch library and evaluation platform for end-to-end compression research
quic/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained...
tensorflow/compression
Data compression in TensorFlow
baler-collaboration/baler
Repository of Baler, a machine learning based data compression tool
thulab/DeepHash
An Open-Source Package for Deep Learning to Hash (DeepHash)