Starred repositories
code for paper "Cross-modal Contrastive Learning for Speech Translation" (NAACL 2022)
润学全球官方指定GITHUB，整理润学宗旨、纲领、理论和各类润之实例；解决为什么润，润去哪里，怎么润三大问题； 并成为新中国人的核心宗教，核心信念。
DAFI: Ensemble based data assimilation and field inversion, repository for internal development
Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
Latex class to render a thesis to UIowa's specifications
A high-level, easy-to-deploy non-uniform Fast Fourier Transform in PyTorch.
Awesome resources on normalizing flows.
Boost LaTeX typesetting efficiency with preview, compile, autocomplete, colorize, and more.
Deep learning for Engineers - Physics Informed Deep Learning
Pytorch implementations of density estimation algorithms: BNAF, Glow, MAF, RealNVP, planar flows
PyTorch implementation of normalizing flow models
HYDRA: Hybrid deep magnetic resonance fingerprinting
Flutter version【膜法指南】open source project
This is an implementation of paper "End-to-end Speech Translation via Cross-modal Progressive Training" (Interspeech2021)
Load MATLAB 7.3 .mat files. I.e. load hdf5 into Python datatypes.
The sample codes for our ICLR18 paper "FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling""
Framework for evaluating Graph Neural Network models on semi-supervised node classification task
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Implementation of the paper "Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism" [AAAI-MLPS 2021]
Deep Learning Based Image Reconstruction for single-source Diffuse Optical Tomography system with sparse measurements
Toast++: Forward and inverse modelling in optical tomography
Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.
Data-driven model reduction library with an emphasis on large scale parallelism and linear subspace methods
Interpolating natural cubic splines. Includes batching, GPU support, support for missing values, evaluating derivatives of the spline, and backpropagation.
Solving inverse problems using conditional invertible neural networks.