Introduction

This project is for personal learning and use, based on MMPreTrain. It aims to track and reproduce the latest backbone models since MMPreTrain hasn’t released any new models for over a year.MMPreTrain is an open source pre-training toolbox based on PyTorch. It is a part of the OpenMMLab project.

The main branch works with PyTorch 1.8+.

What's new

🌟 (2024.12.5) Support StartNet Rewrite the Stars.

• More details StartNet.

🌟 Support CAS-ViT.

• More details CAS-ViT.

Installation

Below are quick steps for installation:

conda create -n BackboneHub python=3.8 pytorch==1.10.1 torchvision==0.11.2 cudatoolkit=11.3 -c pytorch -y
conda activate BackboneHub
pip install openmim
git clone https://github.com/bear-coder-9527/BackboneHub.git
cd BackboneHub
mim install -e .

Please refer to installation documentation for more detailed installation and dataset preparation.

For multi-modality models support, please install the extra dependencies by:

mim install -e ".[multimodal]"

User Guides

The basic usage is same as MMPreTrain for new users:

• Learn about Configs
• Prepare Dataset
• Inference with existing models
• Train
• Test
• Downstream tasks

For more information, please refer to our documentation.

Model zoo

Results and models are available in the model zoo.

Overview

Supported Backbones	Self-supervised Learning	Multi-Modality Algorithms	Others
StarNet CAS-ViT VGG ResNet ResNeXt SE-ResNet SE-ResNeXt RegNet ShuffleNet V1 ShuffleNet V2 MobileNet V2 MobileNet V3 Swin-Transformer Swin-Transformer V2 RepVGG Vision-Transformer Transformer-in-Transformer Res2Net MLP-Mixer DeiT DeiT-3 Conformer T2T-ViT Twins EfficientNet EdgeNeXt ConvNeXt HRNet VAN ConvMixer CSPNet PoolFormer Inception V3 MobileOne EfficientFormer MViT HorNet MobileViT DaViT RepLKNet BEiT MixMIM EfficientNet V2 RevViT ConvNeXt V2 ViG XCiT LeViT RIFormer GLIP ViT SAM EVA02 DINO V2 HiViT	MoCo V1 (CVPR'2020) SimCLR (ICML'2020) MoCo V2 (arXiv'2020) BYOL (NeurIPS'2020) SwAV (NeurIPS'2020) DenseCL (CVPR'2021) SimSiam (CVPR'2021) Barlow Twins (ICML'2021) MoCo V3 (ICCV'2021) BEiT (ICLR'2022) MAE (CVPR'2022) SimMIM (CVPR'2022) MaskFeat (CVPR'2022) CAE (arXiv'2022) MILAN (arXiv'2022) BEiT V2 (arXiv'2022) EVA (CVPR'2023) MixMIM (arXiv'2022) iTPN (CVPR'2023) SparK (ICLR'2023) MFF (ICCV'2023)	BLIP (arxiv'2022) BLIP-2 (arxiv'2023) OFA (CoRR'2022) Flamingo (NeurIPS'2022) Chinese CLIP (arxiv'2022) MiniGPT-4 (arxiv'2023) LLaVA (arxiv'2023) Otter (arxiv'2023)	Image Retrieval Task: ArcFace (CVPR'2019) Training&Test Tips: RandAug AutoAug RepeatAugSampler TTA ...

Acknowledgement

This project is based on MMPreTrain. Thanks for their public repository and excellent contributions!