mirror of
https://github.com/macaodha/batdetect2.git
synced 2026-07-08 05:10:09 +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
39 lines
1.0 KiB
Markdown
39 lines
1.0 KiB
Markdown
# Preprocessing consistency
|
|
|
|
Preprocessing consistency is one of the biggest factors behind stable model
|
|
performance.
|
|
|
|
## Why consistency matters
|
|
|
|
The detector is trained on spectrograms produced by a specific preprocessing
|
|
pipeline.
|
|
If inference uses different settings, the model can see a shifted input
|
|
distribution and performance may drop.
|
|
|
|
Typical mismatch sources:
|
|
|
|
- sample-rate differences,
|
|
- changed frequency crop,
|
|
- changed STFT window/hop,
|
|
- changed spectrogram transforms.
|
|
|
|
## Practical implication
|
|
|
|
When possible, keep preprocessing settings aligned between:
|
|
|
|
- training,
|
|
- evaluation,
|
|
- deployment inference.
|
|
|
|
If you intentionally change preprocessing, treat this as a new experiment and
|
|
re-validate on reviewed local data.
|
|
|
|
## Related pages
|
|
|
|
- Configure audio preprocessing:
|
|
{doc}`../how_to/data/configure-audio-preprocessing`
|
|
- Configure spectrogram preprocessing:
|
|
{doc}`../how_to/data/configure-spectrogram-preprocessing`
|
|
- Preprocessing config reference:
|
|
{doc}`../reference/configs/data/preprocessing-config`
|