432 Open source projects that are alternatives of or similar to Zeroq

PyTorch*-based Neural Network Compression Framework for enhanced OpenVINO™ inference

LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks

All about acceleration and compression of Deep Neural Networks

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

Collections of model quantization algorithms

Pruning and quantization for SSD. Model compression.

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

Stable nginx with google brotli compression module

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

A library for some loosely related Microsoft compression formats, CAB, CHM, HLP, LIT, KWAJ and SZDD.

Fastify compression utils

A self-extracting archiving tool for Unix systems, in 100% shell script.

⚡️ Proxy that compresses images to low-resolution

Heavily optimized zlib compression algorithm

Fast inference engine for OpenNMT models

Create, read and write wav files according to the specs. ⭐️ 🎶 ❤️

Columnar storage extension for Postgres built as a foreign data wrapper. Check out https://github.com/citusdata/citus for a modernized columnar storage implementation built as a table access method.

A hands-on introduction to video technology: image, video, codec (av1, vp9, h265) and more (ffmpeg encoding).

World's Leading Open Source JPEG 2000 Codec

Userspace tools for managing VDO volumes.

Small inflate/deflate implementation in ~300 LoC of ANSI C

Fast decoder for VByte-compressed integers

Reducing the size of convolutional neural networks

Razzle Material-UI example with Styled Components using Express with compression

A variant of include_bytes!/include_str! with compile-time deflation and runtime lazy inflation

A simple JavaScript based client-side image compression algorithm

Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.

Graph Transforms to Quantize and Retrain Deep Neural Nets in TensorFlow

FreeArc'Next

Plain Java unrar library

The Hitchhiker's Guide to Compression

CSS & JavaScript minifier, in PHP. Removes whitespace, strips comments, combines files (incl. @import statements and small assets in CSS files), and optimizes/shortens a few common programming patterns.

Incremental btrfs snapshot backups with push/pull support via SSH

Byte-aligned, efficient lossless packer that is optimized for fast decompression on 8-bit micros

SharpCompress is a fully managed C# library to deal with many compression types and formats.

Limited Error Raster Compression

An equivalent to Actionscript 3's ByteArray for Javascript with AMF0 and AMF3 support.

A Pure C# Class to Store Files in Zip

Study group for algorithms in Ruby, hosted at App Academy

PyTorch implementation of Data Free Quantization Through Weight Equalization and Bias Correction.

Simple Network Encrypting Backup Utility

Implementation of time series compression method from the Facebook's Gorilla paper

R bindings to libarchive, supporting a large variety of archive formats

Easily optimize images using WP CLI

An Open Source Deep Learning Inference Engine Based on FPGA

FrostNet: Towards Quantization-Aware Network Architecture Search

Pure Nim implementation of deflate, zlib, gzip and zip.

A curated list of awesome edge machine learning resources, including research papers, inference engines, challenges, books, meetups and others.

CSS Optimizer(csso) ruby wrapper for Rails Asset pipeline

[ICML 2018] "Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions"

An Android tool to compresses your GIFs into lightweight MP4 video using fast, hardware-accelerated encoders. Supports cropping, rotation, GIF concatenation and much more.

Python Geohash Compression Tool

An efficient delta compression algorithm written in C#

💾 Golang gzip middleware for Gin and net/http | Golang gzip中间件，支持Gin和net/http，开箱即用同时可定制

Powerful, automated analysis and design of quantum microwave chips & devices [Energy-Participation Ratio and more]

WebAssembly powered Deflate/Gzip/Zlib compression for Deno, written in Rust

A high performance and compression ratio compressor for genomic data, powered by GTXLab of Genetalks.

ResNet with Shift, Depthwise, or Convolutional Operations for CIFAR-100, CIFAR-10 on PyTorch

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

Learned image compression