EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]

PeleeNet: An efficient DenseNet architecture for mobile devices

Official code (Tensorflow) for paper "Fast and Efficient Image Quality Enhancement via Desubpixel Convolutional Neural Networks"

CK repository with components and automation actions to enable portable workflows across diverse platforms including Linux, Windows, MacOS and Android. It includes software detection plugins and meta packages (code, data sets, models, scripts, etc) with the possibility of multiple versions to co-exist in a user or system environment.

PeleeNet in PyTorch

Collective Knowledge crowd-tuning extension to let users crowdsource their experiments (using portable Collective Knowledge workflows) such as performance benchmarking, auto tuning and machine learning across diverse platforms with Linux, Windows, MacOS and Android provided by volunteers. Demo of DNN crowd-benchmarking and crowd-tuning:

Collective Knowledge workflow for ARM's workload automation tool: an open framework for gathering and sharing knowledge about system design and optimization using real-world workloads.

Federated Learning (FL) is a collaborative machine learning approach that enables decentralized data processing. Instead of collecting and storing data in a central server, FL trains machine learning models directly on devices or servers where the data resides, enhancing privacy and security.

Курсовая работа по проектированию БД с GUI на PyQt6. Комплексная информационная система для управления каталогом мобильных устройств. Реализована нормализованная PostgreSQL база данных (3НФ), Python/PyQt6 интерфейс с полным CRUD-функционалом и система анализа производительности с 95% оптимизацией запросов.