Docs

The manual and guide text from your BadBob app.

Contents

Comparison · Segmentation

Compare models against the same reference data and evaluation protocol.

Before you start

At least two compatible completed Segmentation results and an available reference dataset.

Quick start

  1. Open Comparison, choose Segmentation and select the candidate runs/models.
  2. Choose common reference data and compare. Inspect per-class behavior and regression examples, not only overall metrics.

Functions and choices

  • Choose candidates

    Choose a reference and one to five compatible candidates before comparing.

  • Use fixed thresholds

    Comparison uses the recorded image size, confidence ≥ 25 percent and match IoU ≥ 50 percent; these are fixed in this view.

Result

Comparable results and documented model differences.

Next step

For Create ML, register a suitable candidate. For Segmentation, select the compatible checkpoint for inference.

All documentation