MPGek
Follow
Stars
The lazier way to manage everything docker
👁️ 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...
Build Real-Time Knowledge Graphs for AI Agents
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
A Kubernetes deployable instance of GroundX for document parsing, storage, and search.
A simple, easy-to-hack GraphRAG implementation
Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
A list of totally open alternatives to ChatGPT
A rewrite of the old legacy software "depends.exe" in C# for Windows devs to troubleshoot dll load dependencies issues.
Free MLOps course from DataTalks.Club
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
A list of Free Software network services and web applications which can be hosted on your own servers
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Simple, online, and realtime tracking of multiple objects in a video sequence.
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Official repository for the paper "Instance-Conditioned GAN" by Arantxa Casanova, Marlene Careil, Jakob Verbeek, Michał Drożdżal, Adriana Romero-Soriano.
Kaggle | 1st place solution for Freesound Audio Tagging 2019
Deep Extreme Cut http://www.vision.ee.ethz.ch/~cvlsegmentation/dextr
A curated list of papers & resources linked to 3D reconstruction from images.
A curated list of awesome awesomeness about artificial intelligence
Awesome Object Detection based on handong1587 github: https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html
A prize winning solution for DFDC challenge
A GPU benchmark tool for evaluating GPUs and CPUs on mixed operational intensity kernels (CUDA, OpenCL, HIP, SYCL, OpenMP)
Тимлид – это ❄️, потому что в каждой компании он уникален и неповторим.