23 个仓库
Libraries for specialized data structures, graphs, and optimization.
Explore 23 awesome GitHub repositories matching part of an awesome list · Data and Graph Processing. Refine with filters or upvote what's useful.
DGL is a Python library for building and training graph neural networks. It functions as a graph message passing framework and a geometric deep learning tool, enabling the development of models that analyze graph-structured data. The library is designed for large-scale graph processing, utilizing distributed training and neighbor sampling to handle datasets with billions of edges. It provides specialized support for heterogeneous graph modeling, allowing for the representation of complex real-world entities with multiple node and edge types. Its capabilities cover a wide range of graph tasks
Package for deep learning on graphs.
torchdiffeq 是一个 PyTorch ODE(常微分方程)求解器库,专为解决初值问题和构建神经 ODE 框架而设计。它提供了一个可微分的 ODE 积分器,允许深度学习模型通过随时间积分动力学函数来模拟连续深度。 该库具有用于内存高效反向传播的伴随法梯度计算器。通过在时间上反向求解增广伴随系统,它可以在不存储每个中间求解器状态的情况下计算参数梯度。 该项目涵盖了具有自适应和固定步长求解器的数值积分,并结合了误差控制和多项式状态插值。它还支持可微分事件管理,以便在特定标量函数触发时终止求解器,并沿事件时间传播梯度。 该框架常用于连续归一化流以及通过学习连续时间常微分方程进行概率分布转换等应用。
Solver for ordinary differential equations.
Kaolin 是一个 PyTorch 3D 深度学习库,提供了一套全面的工具,用于 3D 几何处理、物理模拟、数据可视化和用于计算机视觉的梯度渲染。 该库包括一个可微分的 3D 渲染器和一个用于转换和变换 3D 表示(如网格和点云)的几何处理工具包。它还具有一个 3D 物理模拟引擎,用于计算三维物体和场景之间的物理交互和碰撞。 该工具包提供用于 3D 数据可视化的实用工具,包括创建交互式视图和转盘动画。其他功能涵盖 3D 数据集管理、数据预处理和 3D 表示渲染。
Library for 3D deep learning research.
GPyTorch 是一个 GPU 加速的概率框架和 PyTorch 库,用于实现可扩展的高斯过程模型。它提供了一套用于高斯过程建模和不确定性估计的系统,旨在在图形硬件上执行高效的矩阵运算。 该框架具有一个用于构建自定义协方差函数和建模复杂数据依赖关系的模块化内核系统。它特别将高斯过程与深度神经网络集成,以创建用于回归和分类的混合模型。 该系统采用数值线性代数技术,包括预处理共轭梯度和基于张量的运算,以处理大型数据集。它还支持黑盒变分推理和用于超参数优化的自动微分。
Modular Gaussian process implementation.
Enabling PyTorch on XLA Devices (e.g. Google TPU)
Compiler for connecting the framework to Cloud TPUs.
CVXPYlayers is a Python library for constructing differentiable convex optimization layers in PyTorch, JAX, and MLX using CVXPY. A convex optimization layer solves a parametrized convex optimization problem in the forward pass to produce a solution. It computes the derivative of the solution…
Differentiable convex optimization layers.
A CV toolkit for my papers.
Deep texture encoding network.
Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators
Mobile-optimized quantized neural network operators.
Model analyzer in PyTorch
Model analyzer for performance metrics.
Differentiable rendering without approximation.
Differentiable Monte Carlo path tracer.
Riemannian Adaptive Optimization Methods with pytorch optim
Riemannian adaptive optimization methods.
A multi-model machine learning feature embedding database
Database for machine learning feature embeddings.
TorchANI 2.0 is an open-source library that supports training, development, and research of ANI-style neural network interatomic potentials. It was originally developed and is currently maintained by the Roitberg group.
Neural network potentials for chemistry.
Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)
Fast RNN implementation.