sail-sg/metaformer
A PyTorch implementation of MetaFormer baselines for image classification on ImageNet-1K, including CNN and transformer-based vision models.
Not currently ranked — collecting fresh signals.
star history
This repository provides PyTorch implementations of MetaFormer baselines for vision tasks, specifically IdentityFormer, RandFormer, ConvFormer and CAFormer. The models adopt a hierarchical 4-stage architecture similar to ResNet, with various token mixer designs. ConvFormer outperforms ConvNeXt without novel token mixers, while CAFormer achieves 85.5% accuracy on ImageNet-1K at 224x224 resolution under normal supervised training without external data or distillation.
Frequently asked
- What is sail-sg/metaformer?
- A PyTorch implementation of MetaFormer baselines for image classification on ImageNet-1K, including CNN and transformer-based vision models.
- Is metaformer open source?
- Yes — sail-sg/metaformer is open source, released under the Apache-2.0 license.
- What language is metaformer written in?
- sail-sg/metaformer is primarily written in Python.
- How popular is metaformer?
- sail-sg/metaformer has 500 stars on GitHub.
- Where can I find metaformer?
- sail-sg/metaformer is on GitHub at https://github.com/sail-sg/metaformer.