get_data_generator_inputs

behavenet.data.utils.get_data_generator_inputs(hparams, sess_ids, check_splits=True)

Helper function for generating signals, transforms and paths.

Parameters:

• hparams (dict) – required keys: ‘data_dir’, ‘lab’, ‘expt’, ‘animal’, ‘session’, ‘model_class’, and model parameters associated with the ‘model_class’; see get_transforms_paths() for these parameters

• sess_ids (list of dict) – each list entry is a session-specific dict with keys ‘lab’, ‘expt’, ‘animal’, ‘session’

• check_splits (bool, optional) – check data splits and data rng seed between hparams and loaded model outputs (e.g. latents)

Returns:

• hparams (dict): updated with model-specific information like input and output size

• signals (list): session-specific signals

• transforms (list): session-specific transforms

• paths (list): session-specific paths

Return type:

tuple