Christina Winkler

RevIN. RevIN: Reversible Instance Normalization For Accurate Time-series Forecasting Against Distribution Shift

intro_dgm. "Deep Generative Modeling": Introductory Examples

ML-models. Collection of various ML models for the MaMMoS project

TorchLeet. Leetcode for Pytorch

Time-Series-Works-Conferences. Time-Series Work Summary in CS Top Conferences (NIPS, ICML, ICLR, KDD, AAAI, WWW, IJCAI, CIKM, ICDM, ICDE, etc.)

GCA. [WWW 2021] Source code for "Graph Contrastive Learning with Adaptive Augmentation"

mammos-spindynamics. Spin dynamics package.

DSTAGNN. DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting, which is accepted at ICML2022.

UCR_Time_Series_Classification_Deep_Learning_Baseline. Fully Convlutional Neural Networks for state-of-the-art time series classification

StemGNN. Spectral Temporal Graph Neural Network (StemGNN in short) for Multivariate Time-series Forecasting

fairchem. FAIR Chemistry's library of machine learning methods for chemistry

STFGNN. Code of STFGNN@AAAI-2021 (Spatial-Temporal/ Traffic data forecasting)

MTS-Mixers. MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing

STGODE. Spatial-Temporal Graph ODE Neural Network

MSGNet. MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecasting (AAAI2024)

GLAFF. PyTorch implementation of "Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective" (NeurIPS 2024)

SageFormer. Code for IoTJ 2024 paper "SageFormer: Series-Aware Framework for Long-Term Multivariate Time-Series Forecasting".

phd_thesis_latex_public. LaTeX Sources of my PhD Thesis

Basisformer. This is the pytorch implementation of Basisformer in the Neurips paper: [BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis]

Awesome-Time-Series-Spatio-Temporal. Awesome Time-Series and Spatio-Temporal Related

STGCN_IJCAI-18. [IJCAI'18] Spatio-Temporal Graph Convolutional Networks

awesome-graph-explainability-papers. Papers about explainability of GNNs

GRACE. [GRL+ @ ICML 2020] PyTorch implementation for "Deep Graph Contrastive Representation Learning" (https://arxiv.org/abs/2006.04131v2)

STSGCN. AAAI 2020. Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting

PCRL. Python

papermill. 📚 Parameterize, execute, and analyze notebooks

CoGNN. Python

EvolveGCN. Code for EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

mattergen. Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property constraints.

symbolic_distillation. Symbolic distillation of Neural Networks using SR

fm-boosting. [ECCV 2024, Oral] FMBoost: Boosting Latent Diffusion with Flow Matching

ToonCrafter. [SIGGRAPH Asia 2024, Journal Track] ToonCrafter: Generative Cartoon Interpolation

optuna. A hyperparameter optimization framework

convmag. Conversion between units used in magnetism

nougat. Implementation of Nougat Neural Optical Understanding for Academic Documents

jraph. A Graph Neural Network Library in Jax

GraphXAI. GraphXAI: Resource to support the development and evaluation of GNN explainers

gae-pytorch. Graph Auto-Encoder in PyTorch

clim-var-ds-cnf. This repository contains the code for climate variable downscaling using conditional normalizing flows. Work done during internship @ MILA AI Research. 🛰️

awesome-gnn. A list for GNNs and related works.

ClimateDiffuse. Diffusion for climate downscaling

LION. Learned Iterative Optimization Networks

SegVAE. Implementation of ECCV 2020 paper: "Controllable Image Synthesis via SegVAE". Project page: https://yccyenchicheng.github.io/SegVAE/. Paper: https://arxiv.org/abs/2007.08397.

CDISR. Conditional Diffusion model for 2D Image Super-Resolution(SR). Targets medical images and is inspired from SR3.

gflownet. Generative Flow Networks - GFlowNet

IntegratedGradientsPytorch. Integrated gradients attribution method implemented in PyTorch

vision_transformers_explained. This folder of code contains code and notebooks to supplement the "Vision Transformers Explained" series published on Towards Data Science written by Skylar Callis.

FrEIA. Framework for Easily Invertible Architectures

AISE-2024. ETH Zürich AI in the Sciences and Engineering Master's course 2024

jaxoplanet. Astronomical time series analysis with JAX

torchgeo. TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

papers-for-molecular-design-using-DL. List of Molecular and Material design using Generative AI and Deep Learning

Wavelet-Flow. Wavelet Flow: Fast Training of High Resolution Normalizing Flows

cond-cdvae. An SE(3)-invariant autoencoder for generating the periodic structure of materials [ICLR 2022]

climetlab. Python package for easy access to weather and climate data

AIRS. Artificial Intelligence Research for Science (AIRS)

simple-pytorch-3dgan. A simple and unofficial 3D-GAN implementation using PyTorch [NeurIPS 2016]

3D-GAN-pytorch. Responsible implementation of 3D-GAN NIPS 2016 paper:Learning a Probabilistic Latent Space of ObjectShapes via 3D Generative-Adversarial Modeling,that can be found https://papers.nips.cc/paper/6096-learning-a-probabilistic-latent-space-of-object-shapes-via-3d-generative-adversarial-modeling.pdf

video-diffusion-pytorch. Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch

Diffusion-Models-pytorch. Pytorch implementation of Diffusion Models (https://arxiv.org/pdf/2006.11239.pdf)

skillful_nowcasting. Implementation of DeepMind's Deep Generative Model of Radar (DGMR) https://arxiv.org/abs/2104.00954

machine-learning-of-pdes. Code of my master's thesis on "Physics Informed Machine Learning of Nonlinear Partial Differential Equations"

PDE-VAE-pytorch. PDE-VAE: Variational Autoencoder for Extracting Interpretable Physical Parameters from Spatiotemporal Systems using Unsupervised Learning

FutureGAN. Official PyTorch Implementation of FutureGAN

mdgan. official code of CVPR'18 paper "learning to generate time-lapse videos using multi-stage dynamic generative adversarial networks"

spacetimeformer. Multivariate Time Series Forecasting with efficient Transformers. Code for the paper "Long-Range Transformers for Dynamic Spatiotemporal Forecasting."

deepchem. Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

diffusion-hackathon. Python

galax. Galactic and Gravitational Dynamics in Python (+ GPU and autodiff)

kfac-jax. Second Order Optimization and Curvature Estimation with K-FAC in JAX.

mlops-roadmap-2024.

fab-torch. Flow Annealed Importance Sampling Bootstrap (FAB). ICLR 2023.

flowjax. Python

Multi-Scale-Content-Based-Image-Retrieval. Content-Based Image Retrieval (CBIR) is a significant field within computer vision that empowers efficient exploration and retrieval of images based on their visual content.

GCNNMorphology. Equivariant Nets for Galaxy Classification 🌌🤖

VPTR. The repository for paper VPTR: Efficient Transformers for Video Prediction

transformer. Transformer: PyTorch Implementation of "Attention Is All You Need"

Neural-PDE-Solver.

pytorch-grad-cam. Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

latent-diffusion. High-Resolution Image Synthesis with Latent Diffusion Models

STG-NF. Normalizing Flows for Human Pose Anomaly Detection [ICCV 2023]

MotionFlow. Flow-based Spatio-Temporal Structured Prediction of Dynamics

graph_weather. Graph-based weather forecasting models. Originally, PyTorch implementation of Ryan Keisler's 2022 "Forecasting Global Weather with Graph Neural Networks" paper (https://arxiv.org/abs/2202.07575)

PDEBench. PDEBench: An Extensive Benchmark for Scientific Machine Learning

diffusion-models-for-weather-prediction. Jupyter Notebook

conditional-flow-matching. TorchCFM: a Conditional Flow Matching library

swirl-dynamics. Swirl-Dynamics is a python repository that provides implementations of models, benchmarks and utilities for dynamical systems.

ChemicalNeuralODE. Python

GAMMA. Galactic Attributes of Mass, Metallicity, and Age

PhySR. Physics-informed deep super-resolution of spatiotemporal data

GalacticFlow. Galaxy morphology with conditional normalizing flows

fiftyone. Refine high-quality datasets and visual AI models

jeometric. Graph neural networks in JAX.

FunkNN. Official repo for FunkNN: Neural Interpolation for Functional Generation

equinox. Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

TchAIkovsky. Using JAX to generate piano music as MIDI

GiantMIDI-Piano. Python

pdearena. Python

climate-learn. Source code for ClimateLearn

makani. Massively parallel training of machine-learning based weather and climate models

RainNet. [NeurIPS 2022]RainNet: A Large-Scale Imagery Dataset and Benchmark for Spatial Precipitation Downscaling

ML-For-Beginners. 12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all

generative-ai-for-beginners. 21 Lessons, Get Started Building with Generative AI

Bayesian_CNN. Bayes by Backprop implemented in a CNN

Mendis. Deep Normalising Flows for stellar spectra. It's all about light.

pytorch_remote_sensing_template. A flexible template for setting up deep learning experiments with pytroch and hydra

InfraRender. Python

cgan-superres. super resolution with conditional GANs

SDEdit. PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations

score_sde_pytorch. PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

ProbGAN. [ICLR 2019] ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees

probnum. Probabilistic Numerics in Python.

constrained-downscaling. A project on how to incorporate physics constraints into deep learning architectures for downscaling or other super--resolution tasks.

weatherbench2. A benchmark for the next generation of data-driven global weather models.

Normalizing-Flow-with-Diffusion-Prior-Model. Normalizing Flow with Diffusion Prior Model (NFDPM)

keisler22-predict. This repo contains code for reading weather forecast predictions made using the GNN model of "Forecasting Global Weather with Graph Neural Networks", Keisler 2022.

spate-gan. SPATE-GAN: Improved Generative Modeling of Dynamic Spatio-Temporal Patterns with an Autoregressive Embedding Loss

climart. A benchmark dataset for Machine Learning emulation of atmospheric radiative transfer in weather and climate models (NeurIPS 2021 Datasets and Benchmarks Track)

svg. Python

srvp. Official implementation of the paper Stochastic Latent Residual Video Prediction

WeatherBench. A benchmark dataset for data-driven weather forecasting

ClimateBench. Jupyter Notebook

video_prediction. Stochastic Adversarial Video Prediction

torchtyping. Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.

pytorch_convlstm. convolutional lstm implementation in pytorch

google-research. Google Research

spatio-temporal-GPs. Code for NeurIPS 2021 paper 'Spatio-Temporal Variational Gaussian Processes'

Probabilistic-Downscaling-of-Climate-Variables. Probabilistic Downscaling of Climate Variables Using Denoising Diffusion Probabilistic Models

transformers. 🤗 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.

wassdistance. Approximating Wasserstein distances with PyTorch

educational. Jupyter Notebook

moser_flow. Python

LatentGranger. Python

flowgmm. Shell

GMM_DAE. Python

MscThesis. MSc Computational Statistics and Machine Learning Thesis work.

Physics-Based-Deep-Learning. Links to works on deep learning algorithms for physics problems, TUM-I15 and beyond

ffjord. code for "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models".

torchdiffeq. Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

jax-cfd. Computational Fluid Dynamics in JAX

Nine-Mode-Model. Jupyter Notebook

deep-significance. Enabling easy statistical significance testing for deep neural networks.

JAXFlows. Will wants to learn JAX. He will implement flows.

snf. will plays around with stochastic normalizing flows

torchdyn. A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods

GPy. Gaussian processes framework in python

normalizing_flows. Pytorch implementations of density estimation algorithms: BNAF, Glow, MAF, RealNVP, planar flows

StatisticalMethods. Course notes and resources for Stanford University graduate lecture course PHYS366: Special Topics in Astrophysics: Statistical Methods

Intro-to-Astro-2021. Jupyter Notebook

torchsde. Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

SpectralNET. Jupyter Notebook

autograd. Efficiently computes derivatives of NumPy code.

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

arXausality. A every-so-often-updated collection of every causality + machine learning paper submitted to arXiv in the recent past.

the-art-of-command-line. Master the command line, in one page

wandb. The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

latentCCM. Implementation of the Latent CCM paper

ImageNet-Downsampled. Training code for downsampled ImageNet datasets

pytorch_geometric_temporal. PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)

python-cheatsheet. Comprehensive Python Cheatsheet

torchcde. Differentiable controlled differential equation solvers for PyTorch with GPU support and memory-efficient adjoint backpropagation.

NeuralCDE. Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotlight)

gru_ode_bayes. Pytorch implementation of GRU-ODE-Bayes

releasing-research-code. Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)

black. The uncompromising Python code formatter

iFlow. Identifying through Flows for Recovering Latent Representations, accepted to ICLR2020

ELDR. Explaining Low Dimensional Representations

commit-template-for-humans. An approachable git message template for normal people, including instructions on how to set it up.

uvadlc_practicals_2020. TeX

uvadlc_notebooks. Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023