NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.

OpenMMLab's next-generation platform for general 3D object detection.

中文纠错

Production First and Production Ready End-to-End Speech Recognition Toolkit

Chinese MobileBERT（中文MobileBERT模型）

用 rasa 实现 rasa demo 机器人，有一些惊奇的功能，faq，图谱，多轮等

Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch

QRec: A Python Framework for quick implementation of recommender systems (TensorFlow Based)

Efficient, scalable and enterprise-grade CPU/GPU inference server for Hugging Face transformer models 🚀

使用深度学习算法实现虚拟试衣镜，结合了人体姿态估计、人体分割、几何匹配和GAN，四种模型。仅仅只依赖opencv库就能运行

Span-based system for named entity, relation, and event extraction.

A curated list of resources for Image and Video Deblurring

PDF补丁丁

A curated list of awesome Active Learning

yolov5 prune，Support V2, V3, V4 and V6 versions of yolov5

solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

中文自然语言推理与语义相似度数据集

🕹️ A toolkit for document-level event extraction, containing some SOTA model implementations.

This project aims to explore the deployment of Swin-Transformer based on TensorRT, including the test results of FP16 and INT8.

Collection of recent shadow removal works, including papers, codes, datasets, and metrics.

[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI

benchmark of KgCLUE, with different models and methods

Winners of the Facebook Image Similarity Challenge

Out-of-the-box Annotation Toolbox

Clone a voice in 5 seconds to generate arbitrary speech in real-time

Learning Logic Rules for Document-Level Relation Extraction