Peterou's starred repositories
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
supervision
We write your reusable computer vision tools. 💜
tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
threestudio
A unified framework for 3D content generation.
Inpaint-Anything
Inpaint anything using Segment Anything and inpainting models.
LLM-Agent-Paper-List
The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.
GroundingDINO
Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
sd-webui-segment-anything
Segment Anything for Stable Diffusion WebUI
baby-llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
Semantic-Segment-Anything
Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).
Chinese-LlaMA2
Repo for adapting Meta LlaMA2 in Chinese! META最新发布的LlaMA2的汉化版! (完全开源可商用)
Prompt-Free-Diffusion
Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models, arxiv 2023 / CVPR 2024
Human-Falling-Detect-Tracks
AlphaPose + ST-GCN + SORT.
DualSPHysics
C++/CUDA/OpenMP based Smoothed Particle Hydrodynamics (SPH) Solver
GPT_email_generator
GPT-3 powered professional sounding email generator! Input your direct comments and rephraise will come up with a formal way of getting the message across.
streamlit-image-coordinates
Get the coordinates of clicks on an image in your streamlit app
Cross-modal_Patch_Attack
Unified Adversarial Patch for Cross-modal Attacks in the Physical World
chinese-llama-tokenizer
目标:构建一个更符合语言学的小而美的 llama 分词器,支持中英日三国语言和数门编程语言