fatih akyon

My personal Claude Code and OpenAI Codex setup with battle-tested skills, plugins, hooks and agents that I use daily.

Deep learning based content moderation from text, audio, video & image input modalities.

A lightweight package for converting your labelme annotations into COCO object detection format.

Packaged version of ultralytics/yolov5 + many extra features

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

Packaged, Pytorch-based, easy to use, cross-platform version of the CRAFT text detector

Image comparison slider component for Streamlit

icip2022 paper: sahi benchmark on visdrone and xview datasets using fcos, vfnet and tood detectors

Easiest way of fine-tuning HuggingFace video classification models

Download and convert MIDV-500 annotations to COCO instance segmentation format

Easy to use class balanced cross entropy and focal loss implementation for Pytorch

openai/whisper + extra features

Huggingface utilities for Ultralytics/YOLOv8

Dataset for Intagram Fake and Automated Account Detection

A minimal template for dockerized flask app with redis task queue

A face recognition web app powered by Facenet model using Flask, OpenCV, Heroku

Github Action to deploy conda package to Anaconda repository

A lightweight script for performing Kalman filter based object tracking using MMDetection models.

Object detection and instance segmentation on MaskRCNN with torchvision, albumentations, tensorboard and cocoapi. Supports custom coco datasets with positive/negative samples.

This repo is deprecated. Please refer to new up-to-date repo: https://github.com/fcakyon/craft-text-detector

Confusion Matrix in Python: Plot a pretty confusion matrix (like Matlab) in python using seaborn and matplotlib

IEEE Fraud Detection with XGBoost and CatBoost

A face detection web app powered by SSD face detecctor using Flask, OpenCV, Heroku

ResNet Implementation for CIFAR100 in Pytorch

Official repo for CVPR26 paper "SenBen: Sensitive Scene Graphs for Explainable Content Moderation"

Speech Enhancement Generative Adversarial Network in TensorFlow

Text detection with PSEnet on Pytorch

Use your yolov5 predictions as supervisely annotations

MCP (Model Context Protocol) server support for trackio experiment tracking

Up-to-date earth2.io data

creating this repo to host some turkish nlp datasets

No description.

No description.

Open-source and strong foundation image recognition models.

Faster Whisper transcription with CTranslate2

A general purpose 3D object detection codebse.

Easiest way of combining a music and a video

Instance segmentation ve change detection ile uydu goruntusunden bina tespiti

A pure pytorch implemented ocr project including text detection and recognition

YOLOv3 in PyTorch > ONNX > CoreML > iOS

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.

A simple, fully convolutional model for real-time instance segmentation.

fast image augmentation library and easy to use wrapper around other libraries

Lightweight Facial Analysis Framework for Python Including Face Recognition and Demography (Age, Gender, Emotion and Race)

A curated list of awesome actions to use on GitHub

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

This package provides a DateTime data type, as known from Zope. Unless you need to communicate with Zope APIs, you're probably better off using Python's built-in datetime module.

Find dates inside text using Python and get back datetime objects

No description.

Template for deploying ML models using Flask + Gunicorn + Nginx inside Docker

Please refer to new up-to-date repo: https://github.com/fcakyon/confplot

Code For The Issue Label Bot, an App that automatically labels issues using machine learning, available on the GitHub Marketplace. This is also code for the blog article: "How to automate tasks on GitHub with machine learning for fun and profit"

A Python library to access Instagram's private API.

Personal Instagram Tools

COCO API - Dataset @ http://cocodataset.org/

Derin Öğrenme, Bilgisayarlı Görü, Doğal Dil İşleme ve Pekiştirmeli Öğrenme alanlarındaki uygulama, akademik yayınlar, eğitici kaynaklar ve blog yazılarını bulacağınız yapay öğrenme platformu.

Awesome multilingual OCR toolkits based on PaddlePaddle （practical ultra lightweight OCR system, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices）

The contents of /mnt/skills in Claude's code interpreter environment

A conda-smithy repository for sahi.

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

Bazarr is a companion application to Sonarr and Radarr. It manages and downloads subtitles based on your requirements. You define your preferences by TV show or movie and Bazarr takes care of everything for you.

Effective frame sampling for ML applications.

Retrieval and Retrieval-augmented LLMs

A tutorial on GPT2 language model training with texts from Shakespeare

No description.

An Agnostic Computer Vision Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come

PyTorch Re-Implementation of EAST: An Efficient and Accurate Scene Text Detector

🔥 A bot which scrapes almost everything about a Facebook user's profile including all public posts/statuses available on the user's timeline, uploaded photos, tagged photos, videos, friends list and their profile photos (including Followers, Following, Work Friends, College Friends etc).

UPSNet: A Unified Panoptic Segmentation Network

Pytorch implementation of CTPN (Detecting Text in Natural Image with Connectionist Text Proposal Network)

Waymo Open Dataset

Simple Waymo Open Dataset Reader

ASTER in Pytorch

:camera: Reactive python package for managing, creating and visualizing different deep-learning image annotation formats

Remove a package and its unused dependencies.

This is the repository for the content of inzva Applied AI Study Group.

Scrape reviews from Glassdoor

Train char-rnn with Glassdoor reviews and generate sentences

No description.

OpenMMLab Video Perception Toolbox. It supports Single Object Tracking (SOT), Multiple Object Tracking (MOT), Video Object Detection (VID) with a unified framework.

ONNX Runtime Inference C++ Example

No description.

personal repo for hosting large files

YOLOv4 Implemented in Tensorflow 2.

3D-aware GANs based on NeRF (arXiv).

No description.

Community-curated topic and collection pages on GitHub

OpenMMLab's next-generation platform for general 3D object detection.

No description.

OpenMMLab Computer Vision Foundation

OpenMMLab Detection Toolbox and Benchmark

No description.

Implementing DropPath/StochasticDepth in PyTorch

Bu repo SAHI uygulamasını mantığını öğreniyoruz.

pyntcloud is a Python library for working with 3D point clouds.

Framework to train semantic segmentation models on Pytorch using yaml config files

Your PyTorch AI Factory - Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains

Lightweight Python library for adding real-time object tracking to any detector.

Light Weight Toolkit for Bounding Boxes

A place to submit conda recipes before they become fully fledged conda-forge feedstocks

A deep learning library for video understanding research.

A library for easily evaluating machine learning models and datasets.

The most intuitive, flexible, way for researchers, ML engineers and data scientists to build models (with PyTorch), research workflows and production pipelines with an obsessive focus on flexibility and performance.

Resources for deep learning with satellite & aerial imagery

Fixed version of the facebookresearch/TimeSformer

🕶 A curated list of Tiny Object Detection papers and related resources.

No description.

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

tiny vision language model

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

Ultralytics GitHub Actions

Ultralytics Python Project Template

A Slack MCP server

MCP implementation of Claude Code capabilities and more

A feature-rich command-line audio/video downloader

a state-of-the-art-level open visual language model | 多模态预训练模型

No description.

No description.

Model Context Protocol (MCP) Server for reading from Google Drive and editing Google Sheets

LlamaIndex (GPT Index) is a data framework for your LLM applications

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

No description.

downloading YouTube Videos.

The open-source tool for building high-quality datasets and computer vision models

An amazing UI for OpenAI's ChatGPT (Website + Windows + MacOS + Linux)

We write your reusable computer vision tools. 💜

No description.

No description.

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

A supervisely yolov5 plugin that works on yolov5 v7.0

No description.

Repository which contains links and resources on different topics of Computer Science.

Easy to use pretrained yolov5 models

YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite

A Dark and Light theme with switch for your docsify site

📡 PyTorch Lightning Implementations of Recent Satellite Image Classification !

SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

No description.

OpenMMLab YOLO series toolbox and benchmark

Predicting Traffic Jams with Live Traffic Image Data

No description.

Engineering drawings smart reader

No description.