xiusu/ViTAS
Code for ViTAS_Vision Transformer Architecture Search
This project helps machine learning engineers or researchers automatically design efficient Vision Transformer architectures for image recognition tasks. By defining your computational budget (FLOPs), it takes your image dataset (like ImageNet) and searches for optimal transformer models. The output is a highly efficient, specialized Vision Transformer architecture ready for training and deployment in computer vision applications.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher needing to optimize Vision Transformer models for specific performance and computational constraints without extensive manual architecture design.
Not ideal if you are looking for a pre-trained, off-the-shelf image classification model or do not have access to distributed training infrastructure like Slurm.
Stars
51
Forks
10
Language
Python
License
—
Category
Last pushed
Jul 22, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/xiusu/ViTAS"
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...