Python Low-precision Resources

MOS-Multi-Task-Face-Detect Introduction This repo is the official implementation of "MOS: A Low Latency and Lightweight Framework for Face Detection,

OnsagerNet Learning hidden low dimensional dyanmics using a Generalized Onsager Principle and neural networks This is the original pyTorch implemenati

WinRemoteEnum WinRemoteEnum is a module-based collection of operations achievable by a low-privileged domain user, sharing the goal of remotely gather

A Simple Baseline for Low-Budget Active Learning This repository is the implementation of A Simple Baseline for Low-Budget Active Learning. In this pa

Aircord 🛩️ a discord libary that use to make discord bot with low efficiency and bad performance because I don't know how to manage the project Examp

Automator-Terminator A Proof-of-Concept Layer 2 Denial of Service Attack that disrupts low level operations of Programmable Logic Controllers (PLCs) w

NOD (Night Object Detection) Dataset NOD: Taking a Closer Look at Detection under Extreme Low-Light Conditions with Night Object Detection Dataset, BM

How The New York Times can increase Engagement on Facebook Using machine learning to understand characteristics of news content that garners "high" Fa

ttopt Description Gradient-free global optimization algorithm for multidimensional functions based on the low rank tensor train (TT) format and maximu

ALL Snow Removed: Single Image Desnowing Algorithm Using Hierarchical Dual-tree Complex Wavelet Representation and Contradict Channel Loss (HDCWNet) (

A Collection of Papers and Codes for ICCV2021 Low Level Vision and Image Generation

Torque Limited Simple Pendulum Introduction The project is an open-source and low-cost kit to get started with underactuated robotics. The kit targets

Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset (CVPR'19) Tianyu Wang*, Xin Yang*, Ke Xu, Shaozhe Chen, Qiang Zhang, Ry

DeepFilterNet A Low Complexity Speech Enhancement Framework for Full-Band Audio (48kHz) based on Deep Filtering. libDF contains Rust code used for dat

Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm under Mixed Illumination (ICCV 2021) Dataset License This work is l

Inykcal is a software written in python for selected E-Paper displays. It converts these displays into useful information dashboards. It's open-source, free for personal use, fully modular and user-friendly. Despite all this, Inkycal can run well even on the Raspberry Pi Zero W. Oh, and it's open for third-party modules! Hooray!

Python Image Morpher (PIM) is a program that can take two images and blend them to whatever extent or precision that you like! It is designed to emulate some of Python's OpenCV image processing from scratch without reference.

Control System Packer is a lightweight, low-level program to transform energy equations into the compact libraries for control systems. Packer supports Python 🐍 , C 💻 and C++ 💻 libraries.

A lightweight wrapper for PyTorch that provides a simple declarative API for context switching between devices, distributed modes, mixed-precision, and PyTorch extensions.

Imbalanced Dataset Sampler Introduction In many machine learning applications, we often come across datasets where some types of data may be seen more

BMInf (Big Model Inference) is a low-resource inference package for large-scale pretrained language models (PLMs).

KKBA Intruoduction A low-code tool that generates python crawler code based on curl or url Requirement Python = 3.6 Install pip install kkba Usage Co

SCT This is the official code for the paper "Tracker Meets Night: A Transformer Enhancer for UAV Tracking" The spatial-channel Transformer (SCT) enhan

Streaming speaker diarization Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation by Juan Manuel Coria, Hervé

Streaming speaker diarization Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation by Juan Manuel Coria, Hervé

BanglaBERT This repository contains the official release of the model "BanglaBERT" and associated downstream finetuning code and datasets introduced i

normalizer This python module is an easy-to-use port of the text normalization used in the paper "Not low-resource anymore: Aligner ensembling, batch

DIY Async I/O Creating low-level foundations and abstractions for asynchronous programming in Python (i.e., implementing concurrency without using thr

LLVIP: A Visible-infrared Paired Dataset for Low-light Vision Project | Arxiv | Abstract It is very challenging for various visual tasks such as image

SwinIR: Image Restoration Using Swin Transformer This repository is the official PyTorch implementation of SwinIR: Image Restoration Using Shifted Win

Welcome to the OpenWeedLocator (OWL) project, an opensource hardware and software green-on-brown weed detector that uses entirely off-the-shelf compon

CUDA Python Low-level Bindings

JSON Inline Low code JSON to extract data in one line ENG RU Installation pip install json-inline Usage Rules Modificator Description ?key:value Searc

This project provides abundant choices of quantization strategies (such as the quantization algorithms, training schedules and empirical tricks) for quantizing the deep neural networks into low-bit counterparts.

Nasdaq Cloud Data Service (NCDS) Nasdaq Cloud Data Service (NCDS) provides a modern and efficient method of delivery for realtime exchange data and ot

Seeing Dynamic Scene in the Dark: High-Quality Video Dataset with Mechatronic Alignment This is a pytorch project for the paper Seeing Dynamic Scene i

R2RNet Official code of "R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network." Jiang Hai, Zhu Xuan, Ren Yang, Yutong Hao, Fengzhu

Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

GMPQ: Generalizable Mixed-Precision Quantization via Attribution Rank Preservation This is the pytorch implementation for the paper: Generalizable Mix

One model to speak them all 🌎 Audio Language Text ▷ Chinese 人人生而自由，在尊严和权利上一律平等。 ▷ English All human beings are born free and equal in dignity and rig

Punctuation Restoration using Transformer Models This repository contins official implementation of the paper Punctuation Restoration using Transforme

Performance Ninja Class This is an online course where you can learn to find and fix low-level performance issues, for example CPU cache misses and br

Raspberry Pi 1U Server There are server colocation providers that allow hosting a 1U server for as low as $30/month, but there's a catch: There are re

Prefix date parser This is a helper class to parse dates with varied degrees of precision. For example, a data source might state a date as 2001, 2001

XL-Sum This repository contains the code, data, and models of the paper titled "XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Lang

XL-Sum This repository contains the code, data, and models of the paper titled "XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Lang

EdMIPS is an efficient algorithm to search the optimal mixed-precision neural network directly without proxy task on ImageNet given computation budgets. It can be applied to many popular network architectures, including ResNet, GoogLeNet, and Inception-V3.

An implementation of a floating-point binary fractions class and module in Python. Work with binary fractions and binary floats with ease!

LoRA: Low-Rank Adaptation of Large Language Models This repo contains the implementation of LoRA in GPT-2 and steps to replicate the results in our re

MIRNet Tensorflow implementation of the MIRNet architecture as proposed by Learning Enriched Features for Real Image Restoration and Enhancement. Lanu

MSAD Multi-Scale Aligned Distillation for Low-Resolution Detection Lu Qi*, Jason Kuen*, Jiuxiang Gu, Zhe Lin, Yi Wang, Yukang Chen, Yanwei Li, Jiaya J

Wietse de Vries • Martijn Bartelds • Malvina Nissim • Martijn Wieling Adapting Monolingual Models: Data can be Scarce when Language Similarity is High

Mixed precision training [0] is a technique that mixes the use of full and half precision floating point numbers during training to reduce the memory bandwidth requirements and improve the computational efficiency of a given model.

MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning This repo hosts the code for MetaXL, published at NAACL 2021. [Meta

Graph Evolving Meta-Learning for Low-resource Medical Dialogue Generation Code to be further cleaned... This repo contains the code of the following p

🤗 Accelerate was created for PyTorch users who like to write the training loop of PyTorch models but are reluctant to write and maintain the boilerplate code needed to use multi-GPUs/TPU/fp16.

Under-exposure introduces a series of visual degradation, i.e. decreased visibility, intensive noise, and biased color, etc. To address these problems, we propose a novel semi-supervised learning approach for low-light image enhancement.

HLA-Face: Joint High-Low Adaptation for Low Light Face Detection The official PyTorch implementation for HLA-Face: Joint High-Low Adaptation for Low L

MSAD Multi-Scale Aligned Distillation for Low-Resolution Detection Lu Qi*, Jason Kuen*, Jiuxiang Gu, Zhe Lin, Yi Wang, Yukang Chen, Yanwei Li, Jiaya J

SimplePose Code and pre-trained models for our paper, “Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation”, a

CPT: Efficient Deep Neural Network Training via Cyclic Precision Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, Yingyan Lin Accep

skggm : Gaussian graphical models using the scikit-learn API In the last decade, learning networks that encode conditional independence relationships

Introduction This repository holds NVIDIA-maintained utilities to streamline mixed precision and distributed training in Pytorch. Some of the code her

This repository holds NVIDIA-maintained utilities to streamline mixed precision and distributed training in Pytorch. Some of the code here will be included in upstream Pytorch eventually. The intention of Apex is to make up-to-date utilities available to users as quickly as possible.

HandTailor This repository is the implementation code and model of the paper "HandTailor: Towards High-Precision Monocular 3D Hand Recovery" (arXiv) G

Thug The number of client-side attacks has grown significantly in the past few years shifting focus on poorly protected vulnerable clients. Just as th

EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising By Tengfei Liang, Yi Jin, Yidong Li, Tao Wang. Th

Acorn precision farming rover This is the software repository for Acorn, the precision farming rover by Twisted Fields. For more information see twist

skggm : Gaussian graphical models using the scikit-learn API In the last decade, learning networks that encode conditional independence relationships

Anchor This repository has code for the paper High-Precision Model-Agnostic Explanations. An anchor explanation is a rule that sufficiently “anchors”

GB Renewable Forecast Display This Raspberry Pi powered eInk display aims to give you a quick way to time your home energy usage to help balance the g

BitPack is a practical tool that can efficiently save quantized neural network models with mixed bitwidth.

Multi-Stage Progressive Image Restoration Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, and Ling Sh

scalene: a high-performance CPU and memory profiler for Python by Emery Berger 中文版本 (Chinese version) About Scalene % pip install -U scalene Scalen

Python Elasticsearch Client Official low-level client for Elasticsearch. Its goal is to provide common ground for all Elasticsearch-related code in Py

botocore A low-level interface to a growing number of Amazon Web Services. The botocore package is the foundation for the AWS CLI as well as boto3. On

python-socketio Python implementation of the Socket.IO realtime client and server. Version compatibility The Socket.IO protocol has been through a num

CrossNER is a fully-labeled collected of named entity recognition (NER) data spanning over five diverse domains (Politics, Natural Science, Music, Literature, and Artificial Intelligence) with specialized entity categories for different domains.