🎥 Detect people in real-time with YOLOv8 and receive alerts via Telegram, all in a scalable and easy-to-deploy system.

Software Defined Git Operated Infrastructure

Automated provisioning of workstations and servers.

💙 selected bootc images rolled the way I like it

LUPI-OD - A novel methodology to improve object detection accuracy without increasing model size or complexity. | 2025 European Workshop on Visual Information Processing (EUVIP) | Master of Science Dissertation | University of Malta

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

End-to-end FCOS object detector from scratch in PyTorch, including FPN, centerness, and NMS inference.

SimpleAICV:pytorch training and testing examples.

ZeroTier One as Docker Image

Poor Man's Kubernetes

Terraform module that outputs user_data for a Hetzner Cloud VPS to install Fedora CoreOS with a given Butane config

Pytorch and ncnn implementation of PPYOLOE、YOLOX、PPYOLO、PPYOLOv2、PicoDet and so on.

Templates and scripts to generate a configuration to automatically setup a Linux system on first boot.

This is an object detection web app where users can upload an image, select a detection model, and view the processed image with detected objects. The result is downloadable for further use.

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

Fast and Computationally efficient Continual Learning for NanoDet anchor-free Object Detector

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

In this notebook, we want to recognize the objects in the image using pre-trained models. The used models are fasterRCNN, RetinaNet, SSD and FCOS. The code is programmed in Python language and uses PyTorch and TorchVision library.

Promtail as Docker Image

Multi-Object Tracking Using FCOS + DeepSORT