gw.training.train_pipeline.train_stages

gw.training.train_pipeline.train_stages(pm, wfd, train_dir, local_settings)

Train the network, iterating through the sequence of stages. Stages can change certain settings such as the noise characteristics, optimizer, and scheduler settings.

Parameters

Name	Type	Description	Default
pm	BasePosteriorModel		required
wfd	WaveformDataset		required
train_dir	str	Directory for saving checkpoints and train history.	required
local_settings	dict		required

Returns

Name	Type	Description
	bool	True if all stages are complete False otherwise