「大模型」3小时从头训练一个小参数量的视觉多模态VLM，个人显卡即可推理训练！

Code repository of all OpenGL chapters from the book and its accompanying website https://learnopengl.com

论文写作与资料分享

level-of-details toolkit(LTK). Convert osgb lod tree to 3mx tree. Convert pointcloud in ply/las/laz/xyz to 3mx/osgb tree.

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

Deep Learning-based Image Fusion: A Survey

Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

Truly independent web browser

This repository is a curated collection of the most exciting and influential CVPR 2024 papers. 🔥 [Paper + Code + Demo]

The Cyber Swiss Army Knife - a web app for encryption, encoding, compression and data analysis

自动删除 PC 端微信缓存数据，包括从所有聊天中自动下载的大量文件、视频、图片等数据内容，解放你的空间。

pytorch实用工具

Consistency Distilled Diff VAE

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

[CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

Python bindings for FFmpeg - with complex filtering support

code for paper "Learning to Generate 3D Shapes from a Single Example", SIGGRAPH Asia 2022

文本盲水印：把信息隐匿到文本中，put invisible blind watermark into a text.

Ready-to-use SRT / WebRTC / RTSP / RTMP / LL-HLS media server and media proxy that allows to read, publish, proxy, record and playback video and audio streams.

[ECCV 2020] PyTorch Implementation of some RGBD Semantic Segmentation models.

Ultralytics YOLO11 🚀

Open-source codes and annotated datasets in CVEO recent work "Object-based Classification Framework of Remote Sensing Images with Graph Convolutional Networks" on IEEE Geoscience and Remote Sensing…

OneFormer: One Transformer to Rule Universal Image Segmentation, arxiv 2022 / CVPR 2023

A Python package for segmenting geospatial data with the Segment Anything Model (SAM)

Download tiles from Tile Map Server (online maps) and make a large geo-referenced image