Welcome to Python Object Detection Insights

A library for exploring your object detection dataset. The goal of this library is to provide simple and intuitive visualizations from your dataset and automatically find the best parameters for generating a specific grid of anchors that can fit you data characteristics

Commands

• pyodi paint-annotations - Paint COCO format annotations and predictions
• pyodi ground-truth - Explore your dataset ground truth characteristics.
• pyodi evaluation - Evaluate the predictions of your model against your ground truth.
• pyodi train-config generation - Automatically generate a train_config_file using ground_truth_file.
• pyodi train-config evaluation - Evaluate the fitness between ground_truth_file and train_config_file..
• pyodi coco merge - Automatically merge COCO annotation files.
• pyodi coco split - Creates a new dataset by splitting images into crops and adapting the annotations file
• pyodi crops split - Creates a new dataset by splitting images into crops and adapting the annotations file
• pyodi crops merge - Translate COCO ground truth or COCO predictions crops split into original image coordinates