Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more

flink learning blog. http://www.54tianzhisheng.cn/ 含 Flink 入门、概念、原理、实战、性能调优、源码解析等内容。涉及 Flink Connector、Metrics、Library、DataStream API、Table API & SQL 等内容的学习案例，还有 Flink 落地应用的大型项目案例（PVUV、日志存储、百亿数据实时去…

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Graph Neural Network Library for PyTorch

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

A curated list of awesome self-supervised methods

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

Official PyTorch Implementation of Proxy Anchor Loss for Deep Metric Learning, CVPR 2020

A CV toolkit for my papers.

Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activelo…

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

TRT for WSOL

label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

transformer for sparsely annotated sementic segmentation

[ICIP 2023 (oral)] Team DETR: Guide Queries as a Professional Team in Detection Transformers

[CVPR'23] Learning Neural Parametric Head Models

"Probabilistic Machine Learning" - a book series by Kevin Murphy

🦜🔗 Build context-aware reasoning applications

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021

TePDist (TEnsor Program DISTributed) is an HLO-level automatic distributed system for DL models.

tvm learn follow BBuf

compiler learning resources collect.

how to optimize some algorithm in cuda.

A platform for learning and recording as well as communication.

It is open source ebook about TensorFlow kernel and implementation mechanism.

oneflow runtime actor

C++11 thread