Stars
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）
MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
FaceChain is a deep-learning toolchain for generating your Digital-Twin.
Templating language for generating prompts for text to image generators such as Stable Diffusion
[ICCV 2023 Oral] Text-to-Image Diffusion Models are Zero-Shot Video Generators
The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。
MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
A trusty face analysis research platform developed by Tencent Youtu Lab
Official PyTorch implementation of "Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity" (ICLR'21 Oral)
Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
静默活体检测 Silent Face Anti-Spoofing Attack Detection
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
A PyTorch Implementation of Focal Loss.
ImageNet file xml format to Darknet text format
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors
🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署，支持Android与iOS。
Face ID recognition with medical masks
Code for AAAI 2020 paper, Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks (Disout).
mixup: Beyond Empirical Risk Minimization