wgmueller1

albumentations

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

vaex

Out-of-Core hybrid Apache Arrow/NumPy DataFrame for Python, ML, visualization and exploration of big tabular data at a billion rows per second 🚀

flax

Flax is a neural network library for JAX that is designed for flexibility.

pygcn

Graph Convolutional Networks in PyTorch

stumpy

STUMPY is a powerful and scalable Python library for modern time series analysis

kaggle-web-traffic

1st place solution

bottom-up-attention

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

disentanglement_lib

disentanglement_lib is an open-source library for research on learning disentangled representations.

graphvite

GraphVite: A General and High-performance Graph Embedding System

SIF

sentence embedding by Smooth Inverse Frequency weighting scheme

graph2vec

A parallel implementation of "graph2vec: Learning Distributed Representations of Graphs" (MLGWorkshop 2017).

hand3d

Network estimating 3D Handpose from single color images

kale

Kubeflow’s superfood for Data Scientists

computation-thru-dynamics

Understanding computation in artificial and biological recurrent networks through the lens of dynamical systems.

pandasticsearch

An Elasticsearch client exposing DataFrame API

deep-ttf

Survival analsyis and time-to-failure predictive modeling using Weibull distributions and Recurrent Neural Networks in Keras

dm_memorytasks

A set of 13 diverse machine-learning tasks that require memory to solve.

DeepHit

DeepHit: A Deep Learning Approach to Survival Analysis with Competing Risks

clx

A collection of RAPIDS examples for security analysts, data scientists, and engineers to quickly get started applying RAPIDS and GPU acceleration to real-world cybersecurity use cases.

keras-mdn-layer

An MDN Layer for Keras using TensorFlow's distributions module

PoincareMaps

The need to understand cell developmental processes has spawned a plethora of computational methods for discovering hierarchies from scRNAseq data. However, existing techniques are based on Euclidean geometry which is not an optimal choice for modeling complex cell trajectories with multiple branches. To overcome this fundamental representation issue we propose Poincaré maps, a method harnessing the power of hyperbolic geometry into the realm of single-cell data analysis.

LocalGraphClustering

dnn-binary-code-similarity

Prime

A simple module consistently outperforms self-attention and Transformer model on main NMT datasets with SoTA performance.

WordMoversEmbeddings

WordMoversEmbeddings(WME) is a simple code for generating the vector representation of sentence/document for text classification and clustering.

TADW

An implementation of "Network Representation Learning with Rich Text Information" (IJCAI '15).

DGCNN

blog

boundaries-polarization

Implementation of the algorithm created in "A Measure of Polarization on Social Media Networks Based on Community Boundaries"

T-CorEx

Temporal correlation explanation.