beit 开源项目推荐（23 个）

microsoft /unilm

跨任务、语言和模态的大规模自监督预训练

open-mmlab /mmpretrain

OpenMMPLab预培训收件箱和基准

open-mmlab /mmselfsup

OpenMMLab自我监督学习工作表和基准

PaddlePaddle /PASSL

PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam，SwAV，BEiT，MAE 等图像自监督算法以及 Vision Transformer，DEiT，Swin Transformer，CvT，T2T-ViT，MLP-Mixer，XCiT，ConvNeXt，PVTv2 等基础视觉算法

arxyzan /data2vec-pytorch

PyTorch implementation of "data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language" from Meta AI

pavanpatil45 /BE-Final-Year-Project

BE IT Final Year Machine Learning Project

MohammadRoodbari /Image-Classification

image classification with fine tuning the BEiT vision transformer on CIFAR 10 dataset

JanTeichertKluge /DMLSim

This library provides packages on DoubleML / Causal Machine Learning and Neural Networks in Python for Simulation and Case Studies.

cnmeow /ImageRetrieval

图像检索系统 - Flask Web 应用 - CLIP、BLIP、BEIT

ma-xu /awesome-vision-transformers-comparison

A detailed comparsion of Recent Vision Transformers on ImageNet1k

woctezuma /steam-BEiT

Retrieve Steam games with similar store banners, with Microsoft's Bidirectional Encoder representation from Image Transformers (BEiT).

jianzhnie /self_supervised

self-supervised learning

EliasK93 /BEiT-image-transformer-for-food-classification

Example application for training Microsofts's pretrained BEiT image transformer model on a new image classification task

trungdangtapcode /Flashcard-Recommendation-Extension

Flashcard recommendation based on BEIT and TF score and can be used as normal flashcard extension

AsianZeus /FaceMask-Classification-Models

This repository holds the downstream task of Face Mask Classification performed on Self Currated Custom Dataset with various State of the Art deep learning models like ViT, BeIT, DeIT, LeViT, ConvNeXt, VGG16, EfficientNetV2, RegNet and MobileNetV3.

Abletobetable /smart-product

Predict category of product by it's description, image and other attributes

BastiDood /pal.ai

pal.ai is a progressive web app that uses images of rice leaves to identify rice leaf diseases.

hemanth-maddi /BEiT-based-Alzheimer-s-Classification

Fine-Tuning of BEiT for Alzheimers Disease Classification

anurag965 /Brain-Tumor-Segmentation

Brain tumor semantic segmentation pipeline using a BEiT-based transformer model with attention-driven decoding and skip connections. Handled YOLO/image-based masks, applied advanced augmentations (Albumentations), and used a combined CrossEntropy-Dice loss with class weighting.

Aditya-1874 /Corrupted-Image-Modelling

This project focuses on Corrupted Image Modeling (CiM), where the goal is to train a model capable of reconstructing or enhancing images with missing or corrupted regions. The approach involves learning a robust representation of images to infer and restore missing details.