Guide

📄️ Prepare Training Dataset

A sufficient ODHUB training dataset for object detection includes:

📄️ Create Project

After launching ODHUB, the Select Project window is displayed.

🗃️ Load Training Dataset

2 items

📄️ Model Training

After sending data to the engine, you need to set up the training parameters to start a training experiment. Each training experiment will produce a specific AI model based on the chosen parameters. This means that a project can have multiple models of the same dataset, depending on the number of experiments.

📄️ Evaluate & Export Models

ODHUB provides an intuitive report that helps users choose the best experiment (model) for their object detection application. This information includes model type, final mAP, etc.

📄️ Model Testing

This is optional step that help you to personally verify the model performance and accuracy