Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

A collection of important graph embedding, classification and representation learning papers with implementations.

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

Uncertainty Toolbox: a Python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization

Toolbox of models, callbacks, and datasets for AI/ML researchers.

Implementation of Prototypical Networks for Few Shot Learning (https://arxiv.org/abs/1703.05175) in Pytorch

[IJCAI'18] Spatio-Temporal Graph Convolutional Networks

Pytorch-based framework for solving parametric constrained optimization problems, physics-informed system identification, and parametric model predictive control.

SchNetPack - Deep Neural Networks for Atomistic Systems

A PyTorch implementation of "SimGNN: A Neural Network Approach to Fast Graph Similarity Computation" (WSDM 2019).

NequIP is a code for building E(3)-equivariant interatomic potentials

Calculate Root-mean-square deviation (RMSD) of two molecules, using rotation, in xyz or pdb format

Code for KDD'20 "Generative Pre-Training of Graph Neural Networks"

MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.

Position-aware Graph Neural Networks

Python version of the amazing Reaction Mechanism Generator (RMG).

This is a Pytorch implementation of the paper: Self-Supervised Graph Transformer on Large-Scale Molecular Data

JARVIS-Tools: an open-source software package for data-driven atomistic materials design. Publications: https://scholar.google.com/citations?user=3w6ej94AAAAJ

Keras implementation of a ResNet-CAM model

Fastest Gephi's ForceAtlas2 graph layout algorithm implemented for Python and NetworkX

Representation learning on dynamic graphs using self-attention networks

Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you estimate, communicate and use uncertainty in machine learning model predictions.

Right-size my figures

molSimplify code

[ECCV2024] This is an official implementation for "PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model"

A Python Library for High-Level Semantic Segmentation Models based on TensorFlow and Keras with pretrained backbones.