A package that makes it trivial to create and evaluate machine learning pipeline architectures.

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.

Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation

Spatial modeling using machine learning concepts

A massively parallel, high-level programming language

SQL powered operating system instrumentation, monitoring, and analytics.

Use late-interaction multi-modal models such as ColPali in just a few lines of code.

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

[NeurIPS 2021] Multiscale Benchmarks for Multimodal Representation Learning

A Qt-based fractal viewer

Portable HPC Containers (C++)

Aplicações de Python para Finanças e Investimentos

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Parallel solvers for sparse linear systems featuring multigrid methods.

METIS - Serial Graph Partitioning and Fill-reducing Matrix Ordering

Adaptive FNO transformer - official Pytorch implementation

Initial public release of code, data, and model weights for FourCastNet

Deep Learning for Seismic Imaging and Interpretation

A couple of python scripts to interpret geological structures from geophysical images using deep learning

Graph Attention Networks (https://arxiv.org/abs/1710.10903)

🌀 Clean Architecture with .NET6, C#10 and React+Redux. Use cases as central organizing structure, completely testable, decoupled from frameworks

Public repository for the domain-specific Portuguese word embedding models for the Oil and Gas Industry

🤗 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.

End-to-end learning of deep visual representations for image retrieval

Bioinformatics'2020: BioBERT: a pre-trained biomedical language representation model for biomedical text mining

Links to works on deep learning algorithms for physics problems, TUM-I15 and beyond

TFX is an end-to-end platform for deploying production ML pipelines

Code for the paper "Language Models are Unsupervised Multitask Learners"

Caffe: a fast open framework for deep learning.