Repository Index

Dynamic Tensor Graph library in Clojure (think PyTorch, DynNet, etc.)

:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers, with compute-matched benchmarking and a platform for autonomous architecture research.

• auto-research
• benchmark
• deep-learning
• language-models

Pytorch framework for doing deep learning on point clouds.

Deep and Machine Learning for Microscopy

• microscopy
• materials
• machine-learning
• materials-science

TranslatedAn industrial anomaly detection project based on PatchCore, studying layer2/layer3 score fusion, sensitivity-guided shrinkage, and risk-controlled gating, and providing an engineering-oriented Streamlit demo.

• anomaly-detection
• computer-vision
• feature-fusion
• industrial-anomaly-detection

PyTorch Connectomics: segmentation toolbox for EM connectomics

• computer-vision
• neuroscience
• connectomics
• pytorch

A simple, flexible, and extensible template for PyTorch. It's beautiful.

• deep-learning
• computer-vision
• cnn
• pytorch

TranslatedBuild GPT-2 from scratch in PyTorch, step by step

• attention
• chinese
• deep-learning
• from-scratch

CVPR 2020, "MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps"

• cvpr2020
• autonomous-driving
• perception
• motion-prediction

Free Course : Data, Machine Learning, Deep Learning and AI Engineering, the long way round: the math, the code, the systems and the security. 173 lessons, 166 runnable labs, no shortcuts. Free under CC BY-NC 4.0.

• ai-engineering
• course
• data-engineering
• deep-learning

Modular, fast NLP framework, compatible with Pytorch and spaCy, offering tailored support for French clinical notes.

• nlp
• medical
• text-mining
• clinical-data-warehouse

PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers

• int4
• large-language-models
• pytorch
• quantization

Graph to sequence implemented in Pytorch combining Graph convolutional networks and opennmt-py

PyTorch Geometric Signed Directed is a signed/directed graph neural network extension library for PyTorch Geometric. The paper is accepted by LoG 2023.

• gnn
• graph-neural-netowrks
• signed-networks
• directed-networks

⚡ Open-source software for deep learning-based digital pathology

• deep-learning
• machine-learning
• digital-pathology
• computational-pathology

A graph reliability toolbox based on PyTorch and PyTorch Geometric (PyG).

• adversarial-attacks
• graph-convolutional-networks
• graph-neural-networks
• pytorch

Address book for computer vision models.

• opencv
• open-source
• deep-neural-networks
• tensorflow

RootPainter: Deep Learning Segmentation of Biological Images with Corrective Annotation

• biological-images
• root
• painter
• segmentation

PyTorch implementation of the MIDAS algorithm for single-cell multimodal data integration (Nature Biotechnology 2024).

• deep-generative-model
• deep-learning
• single-cell-data-integration
• single-cell-multiomics

Classification and Gradient-based Localization of Chest Radiographs using PyTorch.

• fine-tuning
• vgg16
• resnet18
• densenet121

An Easy To Use PyTorch Computer Vision Library

• computer-vision
• deep-learning
• pytorch
• pytorch-lightning

MCP server for spatial transcriptomics analysis through natural language interfaces.

• bioinformatics
• cell-communication
• deconvolution
• machine-learning

Multi-stage Riemannian flow matching for physically valid molecular docking, with GNINA scoring, PoseBusters filtering, CLI inference, and benchmarks.

• alphafold3
• docking
• drug-design
• drug-discovery

This repository contains the official PyTorch implementation of GeoDA algorithm. GeoDA is a Black-box attack to generate adversarial example for image classifiers.