3 projects
hawkeyezero
Hawkeye-Zero - special trained model to detect 11 diffrent types of space debris. The idea wasn’t to build a perfect system — just to explore how far object detection can go in real-world space debris applications. Also very important thing was to care about easy and quick access to use model functions and data, so I've created special structure for this project to allowed developers to use model in diffrent environments in API's or as a simple python tool.
yololint
YOLO Dataset Debugger (yololint) is a tool for automatic validation and diagnostics of YOLO-format datasets. It helps you quickly detect common errors, inconsistencies, and missing files in your dataset structure and annotations before you start model training. With clear reports and easy usage, you save time and ensure your dataset is ready for deep learning projects.
litecnn
LiteCNN: Intuitive Python library for creating, training and visualizing convolutional neural networks. Features simplified CNN layer definition, automated training workflows, model visualization, and seamless Keras-to-ONNX conversion. Includes 15 pre-configured popular models for immediate use.
