iamalexkorotin/WassersteinIterativeNetworks
PyTorch implementation of "Wasserstein Iterative Networks for Barycenter Estimation" (NeurIPS 2022)
This helps researchers and practitioners in machine learning and deep learning who need to combine several different image datasets or distributions into a single, representative 'average.' It takes multiple sets of images (like different styles or conditions of celebrity faces or fruits) and produces a high-quality, averaged image dataset that reflects the common characteristics of the inputs. This tool is for those working on generative models, data synthesis, or understanding data distributions.
No commits in the last 6 months.
Use this if you need to create a representative 'average' image dataset from multiple distinct input image collections, especially for benchmarking or developing new generative AI models.
Not ideal if you're looking for a simple image averaging tool for basic photo editing or combining non-distributional image data.
Stars
20
Forks
—
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jul 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/iamalexkorotin/WassersteinIterativeNetworks"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PythonOT/POT
POT : Python Optimal Transport
recursionpharma/gflownet
GFlowNet library specialized for graph & molecular data
IShengFang/SpectralNormalizationKeras
Spectral Normalization for Keras Dense and Convolution Layers
dfdazac/wassdistance
Approximating Wasserstein distances with PyTorch
iamalexkorotin/NeuralOptimalTransport
PyTorch implementation of "Neural Optimal Transport" (ICLR 2023 Spotlight)