A materials discovery algorithm geared towards exploring high-performance candidates in new chemical spaces.
-
Updated
Aug 20, 2024 - Python
A materials discovery algorithm geared towards exploring high-performance candidates in new chemical spaces.
Compact Matlab code for the computation of the 1- and 2-Wasserstein distances in 1D
Calculating Pairwise Similarity of Polymer Ensembles via Earth Mover’s Distance
PyTorch Wrapper for Earth-Mover-Distance (EMD) for 3D point cloud regression
PyTorch code for ACL 2022 paper: RoMe: A Robust Metric for Evaluating Natural Language Generation https://aclanthology.org/2022.acl-long.387/
Code for CVPR 2022 https://arxiv.org/abs/2112.04016 DeepFace-EMD Re-ranking Using Patch-wise Earth Movers Distance Improves Out-Of-Distribution Face Identification
An implementation of Squared Earth-Mover's Distance loss for Neural Networks.
Fast EMD for Python: a wrapper for Pele and Werman's C++ implementation of the Earth Mover's Distance metric
Pillars is a library that contains fast algorithms for Python implemented in Rust.
Earth-movers distance based graph distance metric for financial statements.
Measure the distance between two spectra/signals using optimal transport and related metrics
Morphing and Sampling Network for Dense Point Cloud Completion (AAAI2020)
Reducing MNIST image data dimensionality by extracting the latent space representations of an Autoencoder model. Comparing these latent space representations to the default MNIST representation
3 part project: A. bottleneck autoencoder, B. manhattan distance, C. earth mover's distance
Comparison of multiple methods for calculating MNIST hand-written digits similarity.
Autoencoder dimensionality reduction, EMD-Manhattan metrics comparison and classifier based clustering on MNIST dataset
Autoencoder dimensionality reduction, EMD-Manhattan metrics comparison and classifier based clustering on MNIST dataset.
Jupyter notebook for my research in Document Similarity.
Add a description, image, and links to the earth-movers-distance topic page so that developers can more easily learn about it.
To associate your repository with the earth-movers-distance topic, visit your repo's landing page and select "manage topics."