Ruslan Baikulov

atoMeow. Blue noise stippling in Processing

chatterbox. SoTA open-source TTS

firefox. The official repository of Mozilla's Firefox web browser.

VALI. Video processing in Python

ViV1T. [NeurIPS 2024] 🥉 ViV1T submission in the Sensorium 2023 challenge

shadPS4. PlayStation 4 emulator for Windows, Linux, macOS and FreeBSD written in C++

TileDB. The Universal Storage Engine

tensorstore. Library for reading and writing large multi-dimensional arrays.

zarr-python. An implementation of chunked, compressed, N-dimensional arrays for Python.

AI-project-template. General-purpose structure template for DS/ML/CV/DL/AI projects and Development Style Guide

lz4. Extremely Fast Compression algorithm

alien. ALIEN is a CUDA-powered artificial life simulation program.

sn-spotting. Repository containing all necessary codes to get started on the SoccerNet Action Spotting challenge. This repository also contains several benchmark methods.

ball-action-spotting. SoccerNet@CVPR | 1st place solution for Ball Action Spotting Challenge 2023

GP2040-CE. Multi-Platform Gamepad Firmware for Raspberry Pi Pico and other RP2040 boards

soccernet-calibration-sportlight. SoccerNet@CVPR | 1st place solution for Camera Calibration Challenge 2023

fd. A simple, fast and user-friendly alternative to 'find'

Torch-Pruning. [CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

GPS-Gaussian. [CVPR 2024 Highlight] The official repo for “GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis”

gitea. Git with a cup of tea! Painless self-hosted all-in-one software development service, including Git hosting, code review, team collaboration, package registry and CI/CD

MemoryEncodingModel. [Algonauts 2023] PyTorch implementation of "Memory Encoding Model"

BrainDecodesDeepNets. PyTorch implementation of "Brain Decodes Deep Nets"

actools. Alternative launcher for Assetto Corsa named Content Manager, and some utils as well.

Sunshine. Self-hosted game stream host for Moonlight.

moonlight-qt. GameStream client for PCs (Windows, Mac, Linux, and Steam Link)

SportsLabKit. A python package for turning sports video into csv files

sensorium_2023. repo for the sensorium 2023 competition

voyager. 🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.

open_clip. An open source implementation of CLIP.

pytorch-frame. Tabular Deep Learning Library for PyTorch

gpax. Gaussian Processes for Experimental Sciences

trackerslist. Updated list of public BitTorrent trackers

pyo3. Rust bindings for the Python interpreter

voice-changer. リアルタイムボイスチェンジャー Realtime Voice Changer

audacious. A lightweight and versatile audio player

ViTMatte. [Information Fusion (Vol.103, Mar. '24)] Boosting Image Matting with Pretrained Plain Vision Transformers

soccersegcal. Soccer pitch segmentation and camera calibration in two steps. Step 1, pixelwise segmentation of an broacast image of a soccer game into six different clases defined by the line markings. Step 2, a differential-rendering optimizer that tries to estimate camera parameters from such segementations.Trained on SoccerNet.

quasiqueue. Multiprocessing Queues Made Easy

linesight. AI Plays Trackmania with Reinforcement Learning

kaggle-hubmap-hacking-the-human-vasculature. Solution of Kaggle competition: HuBMAP - Hacking the Human Vasculature

kaggle-asl-fingerspelling-1st-place-solution. 1st place solution to the Google - American Sign Language Fingerspelling Recognition competition

imagehash. A Python Perceptual Image Hashing Module

ml-fastvit. This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023

llama.cpp. LLM inference in C/C++

espnet. End-to-End Speech Processing Toolkit

ParallelWaveGAN. Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

gaussian-splatting. Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

NeRO. [SIGGRAPH2023] NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images

blinker. A fast Python in-process signal/event dispatching system.

flash-attention. Fast and memory-efficient exact attention

engine-sim. Combustion engine simulator that generates realistic audio.

mitsuba3. Mitsuba 3: A Retargetable Forward and Inverse Renderer

UniverSeg. UniverSeg: Universal Medical Image Segmentation

msgspec. A fast serialization and validation library, with builtin support for JSON, MessagePack, YAML, and TOML

AliceVision. 3D Computer Vision Framework

vision. A framework for evaluating models on their alignment to brain and behavioral measurements (100+ benchmarks)

PerspectiveFields. [CVPR 2023 Highlight] Perspective Fields for Single Image Camera Calibration

safetensors. Simple, safe way to store and distribute tensors

V1T. [TMLR 2023] V1T: Large-scale mouse V1 response prediction using a Vision Transformer

HiSup. Python

ggml. Tensor library for machine learning

sdfstudio. A Unified Framework for Surface Reconstruction

nnfabrik. A generalized model fitting pipeline that houses models, trainers, and datasets in datajoint and returns as well as stores trained models.

VOTS2023-Challenge-Tracker. Code for VOTS2023 Challenge tracker

ChordMixer. The official implementation of the ChordMixer architecture.

open-metric-learning. Metric learning and retrieval pipelines, models and zoo.

slovo. Slovo: Russian Sign Language Dataset and Models

BELA. Bi-encoder entity linking architecture

the-turing-way. Book repository for The Turing Way: a how to guide for reproducible, ethical and collaborative data science

ControlNet. Let us control diffusion models!

audiocraft. Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

Otter. 🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

VanillaNet. Python

godot4-demo-desert-light. A graphics demo for Godot 4 - Focus is Volumetric Fog and Indirect Illumination

humanrf. Official code for "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion"

kaggle_rsna_breast_cancer. 1st place solution of RSNA Screening Mammography Breast Cancer Detection competition on Kaggle: https://www.kaggle.com/competitions/rsna-breast-cancer-detection

python-statemachine. Expressive statecharts and FSMs for modern Python.

nvidia-patch. This patch removes restriction on maximum number of simultaneous NVENC video encoding sessions imposed by Nvidia to consumer-grade GPUs.

Stockfish. A free and strong UCI chess engine

XMem. [ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

NeuralPreset. AI-Generated Presets for Faithful 4K Color Style Transfer in Real Time [CVPR 2023]

taichi-nerfs. Implementations of NeRF variants based on Taichi + PyTorch

instant-ngp. Instant neural graphics primitives: lightning fast NeRF and more

typst. A markup-based typesetting system that is powerful and easy to learn.

TriDet. [CVPR2023] Code for the paper, TriDet: Temporal Action Detection with Relative Boundary Modeling

make-a-video-pytorch. Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch

godot-psx-style-demo. Demo project featuring a collection of PS1 style shaders and materials for Godot engine.

jetson_stats. 📊 Simple package for monitoring and control your NVIDIA Jetson [Orin, Xavier, Nano, TX] series

nanoT5. Fast & Simple repository for pre-training and fine-tuning T5-style models

TEXTurePaper. Official Implementation for "TEXTure: Text-Guided Texturing of 3D Shapes"

1st_place_kaggle_player_contact_detection. 1st place code of Player Contact Detection Kaggle competition

godot_spatial_gardener. A Godot plugin for painting plants and props on arbitrary 3D surfaces implemented in GDScript

spot. Code for Spotting Temporally Precise, Fine-Grained Events in Video

pero. Unified Python drawing API

GDExtensionSummator. The Summator Example from Custom Modules made with the GDExtension system in Godot 4

CuVec. Unifying Python/C++/CUDA memory: Python buffered array ↔️ `std::vector` ↔️ CUDA managed memory

ruff. An extremely fast Python linter and code formatter, written in Rust.

godot-4-new-features. Free and open-source Godot 4 demo scenes to see the new features in action

kaggle-rsna-breast-cancer. 6th place solution

python-on-whales. An awesome Python wrapper for an awesome Docker CLI!

lion-pytorch. 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

godot4-oceanfft. Tessendorf FFT based ocean waves and buoyancy in Godot 4 using compute shaders

VideoProcessingFramework. Set of Python bindings to C++ libraries which provides full HW acceleration for video decoding, encoding and GPU-accelerated color space and pixel format conversions

AnimeSR. Codes for "AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos"

FidelityFX-FSR2. FidelityFX Super Resolution 2

Faster-VoxelPose. [ECCV 2022] Official implementation of Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection

SCOPE. Reviatalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation

godot-4-3d-third-person-controller. Godot 4 demo with a plug-and-play 3D Third-Person Shooter (TPS) character controller inspired by games like Ratchet and Clank.

SemanticGuidedHumanMatting. Robust Human Matting via Semantic Guidance, ACCV 2022.

scatter. Godot engine addon to randomly fill an area with props or other scenes. Mirror of https://codeberg.org/hungryproton/proton_scatter

goost. A general-purpose, extensible and customizable C++ extension for Godot Engine.

Gut. Godot Unit Test. Unit testing tool for Godot Game Engine.

auraloss. Collection of audio-focused loss functions in PyTorch

onnxsim. Simplify your onnx model

CORL. High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

BeamNGpy. Python API for BeamNG.tech

godot-shaders. A large library of free and open-source shaders for the Godot game engine. Here, you'll get 2D and 3D shaders with playable demos.

satisfactory-server. A Dockerized version of the Satisfactory dedicated server

mapwatch. [unmaintained] Automatically time your Path of Exile map clears

awakened-poe-trade. :heavy_dollar_sign: :hammer: Path of Exile app for price checking

PathOfBuilding. Offline build planner for Path of Exile.

awesome-godot. A curated list of free/libre plugins, scripts and add-ons for Godot

joplin. Joplin - the privacy-focused note taking app with sync capabilities for Windows, macOS, Linux, Android and iOS.

nanobind. nanobind: tiny and efficient C++/Python bindings

ffcv. FFCV: Fast Forward Computer Vision (and other ML workloads!)

ConvNeXt. Code release for ConvNeXt model

kaggle-solutions. 🏅 Collection of Kaggle Solutions and Ideas 🏅

intel-extension-for-pytorch. A Python package for extending the official PyTorch that can easily obtain performance on Intel platform

portal. 🔵🟠 Portal Explorer — web visualization of mind-blowing portals using ray-tracing.

sahi. Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

layout-parser. A Unified Toolkit for Deep Learning Based Document Image Analysis

awkward. Manipulate JSON-like data with NumPy-like idioms.

pytorch_clip_guided_loss. A simple library that implements CLIP guided loss in PyTorch.

discord-image-captioning-bot. A Discord bot for captioning images

x-clip. A concise but complete implementation of CLIP with various experimental improvements from recent papers

silero-vad. Silero VAD: pre-trained enterprise-grade Voice Activity Detector

bolt. 10x faster matrix and vector operations

overhead-geopose-challenge. Winners of DrivenData's Overhead Geopose Challenge

buggy-resizing-critique. A criticism of a recent paper on buggy image downsampling methods in popular image processing and deep learning libraries.

Swin-Transformer. This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

bfg-repo-cleaner. Removes large or troublesome blobs like git-filter-branch does, but faster. And written in Scala

nogil. Multithreaded Python without the GIL

dacite. Simple creation of data classes from dictionaries.

stylegan3. Official PyTorch implementation of StyleGAN3

lama. 🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

face-detection-tflite. Face and iris detection for Python based on MediaPipe

RobustVideoMatting. Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

tensorpipe. A tensor-aware point-to-point communication primitive for machine learning

YOLOS. [NeurIPS 2021] You Only Look at One Sequence

pedalboard. 🎛 🔊 A Python library for audio.

pytorch-loss. label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

nesmdb. The NES Music Database: use machine learning to compose music for the Nintendo Entertainment System!

moco-v3. PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

temporal-shift-module. [ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

PoseAug. [CVPR 2021 Best Paper Award Candidate] PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation, (Oral, Best Paper Award Finalist)

ots. 🔐 Share end-to-end encrypted secrets with others via a one-time URL

PaintTransformer. Officially unofficial re-implementation of paper: Paint Transformer: Feed Forward Neural Painting with Stroke Prediction, ICCV 2021.

tianshou. An elegant PyTorch deep reinforcement learning library.

opti_models. PyTorch optimizations and benchmarking

pytorch-extension. an example of a CUDA extension for PyTorch using CuPy which computes the Hadamard product of two tensors

moderngl. Modern OpenGL binding for Python

hydra. Hydra is a framework for elegantly configuring complex applications

triton. Development repository for the Triton language and compiler

pytorch_scatter. PyTorch Extension Library of Optimized Scatter Operations

pymatting. A Python library for alpha matting

textual. The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.

guided-diffusion. Python

RecSync-android. Video recording app with sub-millisecond synchronization accuracy for multiple Android smartphones, useful for creating affordable and easy-to-setup multi-view camera systems for robotics, SLAM, 3D-reconstruction, panorama stitching

nanodet. NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

YOLOX. YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

nussl. A flexible source separation library in Python

alphafold. Open source code for AlphaFold 2.

long-short-transformer. Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch

MaskFormer. Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)

convolution-vision-transformers. PyTorch Implementation of CvT: Introducing Convolutions to Vision Transformers

pykka. 🌀 Pykka makes it easier to build concurrent Python applications.

pypeln. Concurrent data pipelines in Python >>>

aioprocessing. A Python 3.5+ library that integrates the multiprocessing module with asyncio

SharedMemoryQueue. A queue implemented using shared memory. 使用共享内存实现的队列

gil_load. Utility for measuring the fraction of time the CPython GIL is held

anyio. High level asynchronous concurrency and networking framework that works on top of either Trio or asyncio

darglint. A python documentation linter which checks that the docstring description matches the definition.

clearml. ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution

dill. serialize all of Python

pathos. parallel graph management and execution in heterogeneous computing

torchinfo. View model summaries in PyTorch!

dramatiq. A fast and reliable background task processing library for Python 3.

trio. Trio – a friendly Python library for async concurrency and I/O

dolt. Dolt – Git for Data

benchmark. TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.

volo. VOLO: Vision Outlooker for Visual Recognition

pikt. :art: Image-based poetic programming language.

sota-music-tagging-models. Python

librosa. Python library for audio and music analysis

pycls. Codebase for Image Classification Research, written in PyTorch.

dask. Parallel computing with task scheduling

xcit. Official code Cross-Covariance Image Transformer (XCiT)

fiftyone. Refine high-quality datasets and visual AI models

organicmaps. 🍃 Organic Maps is a free Android & iOS offline maps app for more than 6M travelers, tourists, hikers, and cyclists. It uses crowd-sourced OpenStreetMap data and is developed with love by the community. No ads, no tracking, no data collection, no crapware. Please donate to support the development!

svox. PlenOctrees construction + rendering PyTorch CUDA extension