mirror of
https://github.com/macaodha/batdetect2.git
synced 2026-07-07 21:00:10 +02:00
67aee0b79c
Some checks failed
CI / Checks (push) Has been cancelled
Docs Pages / Build Docs (push) Has been cancelled
CI / Tests (Python ${{ matrix.python-version }}) (3.10) (push) Has been cancelled
CI / Tests (Python ${{ matrix.python-version }}) (3.11) (push) Has been cancelled
CI / Tests (Python ${{ matrix.python-version }}) (3.12) (push) Has been cancelled
Docs Pages / Deploy Docs (push) Has been cancelled
1.3 KiB
1.3 KiB
How to configure ROI mapping
Use this guide to control how annotation geometry is encoded into training targets and decoded back into boxes.
1) Set the default ROI mapper
The default mapper is anchor_bbox.
roi:
default:
name: anchor_bbox
anchor: bottom-left
time_scale: 1000.0
frequency_scale: 0.001163
2) Choose an anchor strategy
Typical options include bottom-left and center.
bottom-leftis the current default.centercan be easier to reason about in some workflows.
3) Set scale factors intentionally
time_scalecontrols width scaling.frequency_scalecontrols height scaling.
Use values that are consistent with your model setup and keep them fixed when comparing experiments.
4) (Optional) override ROI mapping for specific classes
Add class-specific mappers under roi.overrides.
roi:
default:
name: anchor_bbox
anchor: bottom-left
time_scale: 1000.0
frequency_scale: 0.001163
overrides:
species_x:
name: anchor_bbox
anchor: center
time_scale: 1000.0
frequency_scale: 0.001163
Related pages
- Target definitions:
{doc}
configure-target-definitions - Class definitions:
{doc}
define-target-classes - Target encoding overview:
{doc}
../../explanation/target-encoding-and-decoding