zabaras/inn-surrogate
Solving inverse problems using conditional invertible neural networks.
This project helps engineers and scientists in fields like fluid dynamics or materials science to quickly determine unknown physical properties of a system. By inputting observable data, such as pressure or saturation readings, it directly outputs the underlying spatially-dependent parameters, like permeability fields. This tool is ideal for researchers and practitioners who need to infer hidden system characteristics from limited measurement data.
No commits in the last 6 months.
Use this if you need to rapidly estimate unknown, spatially-varying physical parameters of a system from a small set of observations, especially in scenarios governed by complex partial differential equations.
Not ideal if you are looking to build a forward model to predict system behavior given known inputs, rather than inferring inputs from observed outputs.
Stars
33
Forks
9
Language
Python
License
MIT
Category
Last pushed
Mar 23, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zabaras/inn-surrogate"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
YU1ut/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
kamata1729/QATM_pytorch
Pytorch Implementation of QATM:Quality-Aware Template Matching For Deep Learning
nttcslab/msm-mae
Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations
rgeirhos/generalisation-humans-DNNs
Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)