bafatah

llm.c

LLM training in simple, raw C/CUDA

iTPN

(CVPR2023/TPAMI2024) Integrally Pre-Trained Transformer Pyramid Networks -- A Hierarchical Vision Transformer for Masked Image Modeling

VMamba

VMamba: Visual State Space Models，code is based on mamba

Vim

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

U-Mamba

U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation

ViT-FL-main

PFLlib

We expose this user-friendly algorithm library (with an integrated evaluation platform) for beginners who intend to start federated learning (FL) study

Sageflow

Sageflow: Robust Federated Learning against Both Stragglers and Adversaries at NeurIPS'21

bispectral-networks

Official PyTorch implementation of Bispectral Neural Networks, ICLR 2023

FedProx

Federated Optimization in Heterogeneous Networks (MLSys '20)

PersonalizedFL

Personalized federated learning codebase for research

wassdistance

Approximating Wasserstein distances with PyTorch

LM

A Python module to train simple multi-layer perceptron neural networks using Levenberg-Marquardt training

probabilistic-federated-neural-matching

Bayesian Nonparametric Federated Learning of Neural Networks

FedDyn

PerCom2021-FL

Federated_learning codes used for the the paper "Evaluation of Federated Learning Aggregation Algorithms" and "A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison"

FedMA

Code for Federated Learning with Matched Averaging, ICLR 2020.

wise-ft

Robust fine-tuning of zero-shot models

PruneFL

This is the code repository for the following paper: "Model pruning enables efficient federated learning on edge devices".

dissect-git-re-basin

Replicating and dissecting the git-re-basin project in one-click-replication Colabs

git-re-basin

Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"

Deep-Learning-Projects

This repo contains projects related to Vision, NLP and Reinforcement Learning

RoadDamageDetector