DeepSeek Harness: Everything is a Plugin.

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Algorithm powering the For You feed on X

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Minimal reproduction of DeepSeek R1-Zero

Reproduce R1 Zero on Logic Puzzle

Fully open reproduction of DeepSeek-R1

deep learning for image processing including classification and object-detection etc.

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

推荐系统入门教程，在线阅读地址：https://datawhalechina.github.io/fun-rec/

My blogs and code for machine learning. http://cnblogs.com/pinard

CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition

本项目采用Keras和Keras-bert实现中文序列标注，对BERT进行微调，并在多个命名实体识别数据集上进行测试。

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Implementation of BERT that could load official pre-trained models for feature extraction and prediction

Google AI 2018 BERT pytorch implementation

PyTorch code and models for the DINOv2 self-supervised learning method.

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

Apollo is a reliable configuration management system suitable for microservice configuration management scenarios.

A deep matching model library for recommendations & advertising. It's easy to train models and to export representation vectors which can be used for ANN search.

Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Alignedreid＋+: Dynamically Matching Local Information for Person Re-Identification.

[ECCV2022] PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification

ModelScope: bring the notion of Model-as-a-Service to life.

Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models