Globox: Multi-Format Object Detection Annotation and Evaluation Suite

Supporting 6+ annotation formats including COCO and YOLO, this resource by laclouis5 provides standardized tools for object detection evaluation as of February 2026. It enables the calculation of mean Average Precision metrics for bounding box accuracy across diverse computer vision datasets.

Use Cases

• Converting YOLO format annotations to COCO JSON for use in standard evaluation scripts
• Calculating PascalVOC mAP metrics to benchmark object detection model accuracy
• Standardizing LabelMe bounding box data into a unified format for multi-source training

Strengths

• Supports 6+ annotation formats including CVAT and OpenImage
• Includes built-in COCO and PascalVOC evaluation metrics
• Maintained with an MIT license for open integration

Limitations

• Does not provide raw image data or pre-labeled datasets
• Requires external Python environment to execute conversion logic

Provenance

Source

laclouis5 on GitHub

Freshness

Last updated February 2026