Skip to content

Nm Training Placeholder

Source

Placeholder code snippets for noise model training integration.

This module contains template/placeholder code that demonstrates how noise model training could be integrated into CAREamist. These are reference implementations and should not be imported or used directly.

train_noise_model(self, clean_data, noisy_data, learning_rate=0.1, batch_size=250000, n_epochs=2000, lower_clip=0.0, upper_clip=100.0, save_noise_models=True)

Train noise models from clean/noisy data pairs.

Parameters:

Name Type Description Default
self object

CAREamist instance.

 required
clean_data Union[Path, str, NDArray]

Clean (signal) data for training noise models.

 required
noisy_data Union[Path, str, NDArray]

Noisy (observation) data for training noise models.

 required
learning_rate float

Learning rate for noise model training.

 1e-1
batch_size int

Batch size for noise model training.

 250000
n_epochs int

Number of epochs for noise model training.

 2000
lower_clip float

Lower percentile for clipping training data.

 0.0
upper_clip float

Upper percentile for clipping training data.

 100.0
save_noise_models bool

Whether to save trained noise models to disk.

 True

Raises:

Type Description
ValueError

If noise models are not initialized for training.
ValueError

If data shapes don't match expectations.