PyBigStar (lsl1229840757)

lsl1229840757

Geek Repo

Company:LIESMARS of Wuhan University

Location:Wuhan, China

Github PK Tool:Github PK Tool

PyBigStar's starred repositories

Weighted-Boxes-Fusion

Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.

Language:PythonLicense:MITStargazers:1703Issues:0Issues:0

active_indexing

Official implementation of "Active Image Indexing"

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:57Issues:0Issues:0

perception_test_iccv2023

Champion Solutions repository for Perception Test challenges in ICCV2023 workshop.

Language:PythonLicense:MITStargazers:10Issues:0Issues:0

AnypatternStyle

The style extractor trained on AnyPattern

Language:PythonLicense:MITStargazers:5Issues:0Issues:0

AnyPattern

The official implementation of "AnyPattern: Towards In-context Image Copy Detection"

Language:PythonLicense:MITStargazers:6Issues:0Issues:0

StyleShot

StyleShot: A SnapShot on Any Style. 一款可以迁移任意风格到任意内容的模型,无需针对图片微调,即能生成高质量的个性风格化图片!

Language:PythonLicense:MITStargazers:131Issues:0Issues:0

YOLOv8-TensorRT-CPP

YOLOv8 TensorRT C++ Implementation

Language:C++License:MITStargazers:497Issues:0Issues:0

LLM101n

LLM101n: Let's build a Storyteller

Stargazers:25301Issues:0Issues:0

Algorithm-Practice-in-Industry

搜索、推荐、广告、用增等工业界实践文章收集(来源:知乎、Datafuntalk、技术公众号)

Language:PythonLicense:BSD-2-ClauseStargazers:1896Issues:0Issues:0

CUDA-Learn-Notes

🎉CUDA&C++ 笔记 / 大模型手撕CUDA / 技术博客,更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.

Language:CudaLicense:GPL-3.0Stargazers:910Issues:0Issues:0

momentum

A library for human kinematic motion and numerical optimization solvers to apply human motion

Language:C++License:MITStargazers:84Issues:0Issues:0

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

Language:Jupyter NotebookLicense:BSD-3-ClauseStargazers:9293Issues:0Issues:0

openai-cookbook

Examples and guides for using the OpenAI API

Language:MDXLicense:MITStargazers:57812Issues:0Issues:0

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Language:PythonLicense:MITStargazers:11265Issues:0Issues:0

OmniCorpus

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

Stargazers:200Issues:0Issues:0

VMamba

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

Language:PythonLicense:MITStargazers:1892Issues:0Issues:0
Language:Jupyter NotebookLicense:Apache-2.0Stargazers:173Issues:0Issues:0

lama

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:7615Issues:0Issues:0

zeta

Build high-performance AI models with modular building blocks

Language:PythonLicense:Apache-2.0Stargazers:333Issues:0Issues:0

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

Language:ShellStargazers:6474Issues:0Issues:0

ShareGPT4Video

An official implementation of ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

Language:PythonStargazers:1177Issues:0Issues:0

Instruct-ReID

A General-purpose Person Re-identification Task with Instructions

Language:PythonStargazers:91Issues:0Issues:0

flash-diffusion

Official implementation of ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation

Language:PythonLicense:NOASSERTIONStargazers:397Issues:0Issues:0

VisionMamba

Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images

Language:PythonLicense:MITStargazers:317Issues:0Issues:0

MotionLLM

[Arxiv-2024] MotionLLM: Understanding Human Behaviors from Human Motions and Videos

Language:PythonLicense:NOASSERTIONStargazers:188Issues:0Issues:0

LoRA-Ensemble

LoRA-Ensemble: Efficient Uncertainty Modelling for Self-attention Networks

Language:PythonLicense:MITStargazers:32Issues:0Issues:0

Skywork-MoE

Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models

Stargazers:118Issues:0Issues:0

AutoPrompt

A framework for prompt tuning using Intent-based Prompt Calibration

Language:PythonLicense:Apache-2.0Stargazers:1918Issues:0Issues:0

edm2

Analyzing and Improving the Training Dynamics of Diffusion Models (EDM2)

Language:PythonLicense:NOASSERTIONStargazers:427Issues:0Issues:0