awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
facebookresearch avatar

facebookresearch/ConvNeXt-V2Archived

0
View on GitHub↗
2,053 stars·171 forks·Python·7 views

ConvNeXt V2

This repo contains the PyTorch version of 8 model definitions (Atto, Femto, Pico, Nano, Tiny, Base, Large, Huge), pre-training/fine-tuning code and pre-trained weights (converted from JAX weights trained on TPU) for our ConvNeXt V2 paper.

Features

  • Attention Free Architectures - Co-designs and scales ConvNets using masked autoencoders.
  • Vision Transformers - Scaling convnets using masked autoencoders and transformer-inspired designs.

Star history

Star history chart for facebookresearch/convnext-v2Star history chart for facebookresearch/convnext-v2

How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Frequently asked questions

What does facebookresearch/convnext-v2 do?

This repo contains the PyTorch version of 8 model definitions (Atto, Femto, Pico, Nano, Tiny, Base, Large, Huge), pre-training/fine-tuning code and pre-trained weights (converted from JAX weights trained on TPU) for our ConvNeXt V2 paper.

What are the main features of facebookresearch/convnext-v2?

The main features of facebookresearch/convnext-v2 are: Attention Free Architectures, Vision Transformers.

What are some open-source alternatives to facebookresearch/convnext-v2?

Open-source alternatives to facebookresearch/convnext-v2 include: huawei-noah/cv-backbones — CV-Backbones is a computer vision backbone library and model zoo providing a collection of pre-defined neural network… aliborji/splitmixer. alinlab/remixer. amazon-research/anti-aliasing-transformer. amoza-theodore/mdmlp. ailab-cvc/groupmixformer.

Open-source alternatives to ConvNeXt V2

Similar open-source projects, ranked by how many features they share with ConvNeXt V2.
  • huawei-noah/cv-backboneshuawei-noah avatar

    huawei-noah/CV-Backbones

    4,416View on GitHub↗

    CV-Backbones is a computer vision backbone library and model zoo providing a collection of pre-defined neural network architectures for extracting visual features and processing image data. It serves as a PyTorch vision framework of reusable deep learning components designed for image analysis and visual representation learning. The library focuses on efficient neural network architectures to reduce computational overhead while maintaining feature extraction performance. This is achieved through the implementation of lightweight model designs such as GhostNet and MLP. The project covers a br

    Python
    View on GitHub↗4,416
  • aliborji/splitmixerA

    aliborji/splitmixer

    0View on GitHub↗
    View on GitHub↗0
  • alinlab/remixerA

    alinlab/remixer

    0View on GitHub↗
    View on GitHub↗0
  • ailab-cvc/groupmixformerA

    AILab-CVC/GroupMixFormer

    0View on GitHub↗
    View on GitHub↗0
See all 30 alternatives to ConvNeXt V2
→