Sense-X/UniNet
Unified Architecture Search with Convolution, Transformer, and MLP (ECCV 2022)
UniNet provides a cutting-edge toolkit for researchers and machine learning engineers to build and evaluate advanced image recognition models. It allows you to automatically design efficient neural network architectures that combine different building blocks like convolutions, transformers, and MLPs. You input your image dataset and it helps you find the best model configuration for high accuracy.
No commits in the last 6 months.
Use this if you are an AI/ML researcher or practitioner looking to develop state-of-the-art image classification models and want to explore novel, unified network architectures.
Not ideal if you need a simple, off-the-shelf image classification solution without needing to engage in architecture search or complex model development.
Stars
53
Forks
1
Language
Python
License
MIT
Category
Last pushed
Dec 20, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Sense-X/UniNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepinv/deepinv
DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning
yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.