328 Open source projects that are alternatives of or similar to entity-embed

🧶 Modular VAE disentanglement framework for python built with PyTorch Lightning ▸ Including metrics and datasets ▸ With strongly supervised, weakly supervised and unsupervised methods ▸ Easily configured and run with Hydra config ▸ Inspired by disentanglement_lib

This is project page for the paper "RG-Flow: a hierarchical and explainable flow model based on renormalization group and sparse prior". Paper link: https://arxiv.org/abs/2010.00029

Whitening for Self-Supervised Representation Learning | Official repository

Ladder Variational Autoencoders (LVAE) in PyTorch

A list of free data matching and record linkage software.

Locality Sensitive Hashing using MinHash in Python/Cython to detect near duplicate text documents

Fast, secure, efficient backup program

A pair of kernel modules which provide pools of deduplicated and/or compressed block storage.

Find duplicate files

Quickly detect already witnessed data.

Userspace tools for managing VDO volumes.

Spark RDD with Lucene's query and entity linkage capabilities

Make it easier to compare and cross-reference the names of companies and people by applying strong normalisation.

Record Linkage ToolKit (Find and link entities)

Extremely fast tool to remove duplicates and other lint from your filesystem

FastCDC implementation in Rust

📊 python package for performing deduplication using flexible text matching and cleaning in pandas dataframe

Simple, configuration-driven backup software for servers and workstations

A powerful duplicate file finder and an enhanced fork of 'fdupes'.

Data deduplication engine, supporting optional compression and public key encryption.

Straightforward fuzzy matching, information retrieval and NLP building blocks for JavaScript.

A toolkit for record linkage and duplicate detection in Python

Cross-platform backup tool for Windows, macOS & Linux with fast, incremental backups, client-side end-to-end encryption, compression and data deduplication. CLI and GUI included.

Prometheus Alertmanager

Dedupe/batch geocode addresses and venues around the world with libpostal

Accelerating the deduplication and collapsing process for reads with Unique Molecular Identifiers (UMI). Heavily optimized for scalability and orders of magnitude faster than a previous tool.

RocketMQ消息幂等去重消费者，支持使用MySQL或者Redis做幂等表，开箱即用

Generate duplex/single consensus reads to reduce sequencing noises and remove duplications