![cpp logo](https://raw.githubusercontent.com/github/explore/180320cffc25f4ed1bbdfd33d4db3a66eeeeb358/topics/cpp/cpp.png)
Block or Report
Block or report safeanimal
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseLists (9)
Sort Name ascending (A-Z)
Language
Sort by: Recently starred
Starred repositories
It is said that, Ilya Sutskever gave John Carmack this reading list of ~ 30 research papers on deep learning.
PyTorch code and models for the DINOv2 self-supervised learning method.
AI语义搜索本地素材。以图搜图、查找本地素材、根据文字描述匹配画面、视频帧搜索、根据画面描述搜索视频。Semantic search. Search local photos and videos through natural language.
《美国反对美国》是王沪宁先生在上世纪80年代末赴美观察写作的。我们知道在那个年代中国对西方特别是美国的追捧有多高,所以突然看到一个学者在80年代就有如此清楚的认识,十分钦佩。由于网上只有效果很差的PDF扫描版,所以我想利用OCR技术和肉眼(人体OCR)来转成现代化的文本格式。目前已经全部完成。
猫抓 浏览器资源嗅探扩展 / cat-catch Browser Resource Sniffing Extension
A generative speech model for daily dialogue.
EdgeFace: Efficient Face Recognition Model for Edge Devices [TBIOM 2024] the winner of compact track of IJCB 2023 Efficient Face Recognition Competition
[CVPR 2024 Highlight] Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis
Implementation code:Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
Implementation code:Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
Rotated Rectangle Crop Function for OpenCV
[ICCV 2023] Controllable Person Image Synthesis with Pose‑Constrained Latent Diffusion
Official Implementation for "Cross Attention Based Style Distribution for Controllable Person Image Synthesis" (ECCV2022))
A visual no-code/code-free web crawler/spider易采集:一个可视化浏览器自动化测试/数据采集/爬虫软件,可以无代码图形化的设计和执行爬虫任务。别名:ServiceWrapper面向Web应用的智能化服务封装系统。
An open-source academic paper management tool.
MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone
Easy-to-use and high-performance NLP and LLM framework based on MindSpore, compatible with models and datasets of 🤗Huggingface.
Making large AI models cheaper, faster and more accessible
Official implementation of "Composer: Creative and Controllable Image Synthesis with Composable Conditions"
An out-of-box human parsing representation extractor.
Human body part segmentation model, trained with 22 class labels.
🔎 A plugin to index posts of your Hexo blog on Algolia