Aprendizaje automático · GitHub

Augmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes

R interface for Apache Spark

torch sparse linear algebra library

• Differentiable: gradients flow through solves, factorizations, and eigensolves via torch.autograd
• Six verified backends: pytorch native Krylov (CPU/CUDA/ROCm), scipy (CPU), cudss (NVIDIA CUDA), strumpack direct (CPU/CUDA/ROCm), pyamg (CPU), amgx (NVIDIA CUDA) — each checked to ‖Ax−b‖/‖b‖ at or near machine precision

SPDlearn: A Geometric Deep Learning Python Library for Neural Decoding Through Trivialization

• SPD Layers — Specialized neural network layers for SPD matrices: BiMap for bilinear mappings, ReEig for eigenvalue rectification, and LogEig for tangent space projection.
• Riemannian Operations — Complete toolkit for SPD manifold computations: exponential/logarithmic maps, geodesic distances, Log-Euclidean mean, and geodesic interpolation.

A PyTorch Lightning extension that accelerates and enhances foundation model experimentation with flexible fine-tuning schedules.

CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).

Local ONNX classification of torrent and media metadata, with optional catalogue and swarm estimates.

Iris-3B: pixel-space generation & general vision learner. A 3B diffusion transformer that generates every pixel directly (no VAE); the same prior, fine-tuned, does monocular depth estimation and 4x image restoration. Paper, weights, training code and demo.

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations by T. Chen et al.

🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.

Combina SQL e IA.

Gaining advanced insights from Git repository history.

Large scale K-means and K-nn implementation on NVIDIA GPU / CUDA

Resuelve rompecabezas. Mejora tus conocimientos de PyTorch.