Midv260 Full [portable] Official

To help me create the correct report for you, could you double-check the name or provide a bit more context? For example:

• Detection: IoU, Average Precision (AP) for bounding boxes/polygons.
• OCR: Character Error Rate (CER), Word Error Rate (WER), field-level accuracy.
• Layout: mIoU or mean Average Precision for region segmentation.
• End-to-end: Combined metrics that measure correct detection + correct field recognition.

The "260" in MIDV-260 refers to the specific number of identity document template classes contained within the dataset. midv260 full

MIDV-500

Since the release of MIDV-260, the collection has expanded. The dataset is part of a larger family of research tools, including: : An expanded version featuring 500 document types. To help me create the correct report for