機械学習 · GitHub

Samples for getting started with deep learning across TensorFlow, CNTK, Theano and more.

A low-latency & high-throughput serving engine for LLMs

Spectral Temporal Graph Neural Network (StemGNN in short) for Multivariate Time-series Forecasting

アマデウス Memory storage and artificial intelligence system. Complex chatting AI bot for discord, also voice / music, streams trackers, WarCraft3 news, games trackers, various statistics/info grabbers.

• Too many small commands
• Slash commands support (type /)

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

High performance C++ library for neural amp modeler (NAM) and other audio network models

Python code accompanying the course "A deep understanding of deep learning (with Python intro)"

Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning

A data pipeline framework for machine learning

Lagrangian Neural Networks

Code for "Discovering Symbolic Models from Deep Learning with Inductive Biases"

PyTorch实现高分遥感语义分割（地物分类）

Performance-optimized wheels for TensorFlow (SSE, AVX, FMA, XLA, MPI)

Lightwood is Legos for Machine Learning.

mmdetection源码注释

Collection of recent methods on (deep) neural network compression and acceleration.

Pre-train Static Word Embeddings

A review of change detection methods, including codes and open data sets for deep learning. From paper: change detection based on artificial intelligence: state-of-the-art and challenges.

Allegro is a code for building highly scalable E(3)-equivariant interatomic potentials

LAMMPS pair styles for NequIP and Allegro deep learning interatomic potentials