Stars
(ECCV 2024) VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation
[NeurIPS 2023] This repo contains the code for our paper Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
This is a new model which can segment objects selected via text prompt. Built on the recently released model, EfficientSAM, and the GroundingDINO detection model, it's an easy-to-use and effective …
Isaac Gym Environments for Legged Robots
本仓库主要提供【哈工大航天与自动化大类——飞行器设计/自动化/小卫星专业培养方案】所涵盖课程资料。包括专业培养方案、Xmind课程笔记、课程教材及其他资料。
✔(已完结)最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】
CSSegmentation: An Open Source Continual Semantic Segmentation Toolbox Based on PyTorch.
A book for Learning the Foundations of LLMs
Repository of code to study the impacts of LoRA and ConvLoRa in terms of avoiding Catastrophic Forgetting to Dynamic Networks group.
Tinymind - Write and sync your blog & thoughts with GitHub
按照锤子便签调整的markdown-css 主题。
一键同步文章到多个内容平台,支持今日头条、WordPress、知乎、简书、掘金、CSDN、typecho各大平台,一次发布,多平台同步发布。解放个人生产力
✍ WeChat Markdown Editor | 一款高度简洁的微信 Markdown 编辑器:支持 Markdown 语法、自定义主题样式、内容管理、多图床、AI 助手等特性
整理开源的中文大语言模型,以规模较小、可私有化部署、训练成本较低的模型为主,包括底座模型,垂直领域微调及应用,数据集与教程等。
🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox
Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality (NeurIPS 2023, Spotlight)
Download images from Google, Bing, Baidu. 谷歌、百度、必应图片下载.
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
Fine tuning OpenAI's CLIP model on Indian Fashion Dataset
4th place solution for the Google Universal Image Embedding Kaggle Challenge. Instance-Level Recognition workshop at ECCV 2022