export_states

behavenet.fitting.eval.export_states(hparams, data_generator, model, filename=None)[source]

Export predicted latents using an already initialized data_generator and model.

States are saved based on the hparams dict unless another file is provided. The default filename is [lab_id]_[expt_id]_[animal_id]_[session_id]_states.pkl.

Parameters:

  • hparams (dict) – needs to contain ‘expt_dir’ and ‘version’

  • data_generator (ConcatSessionGenerator object) – data generator to use for latent creation

  • model (HMM object) – ssm model

  • filename (str or NoneType, optional) – absolute path to save latents; if NoneType, latents are stored in model directory

Returns:

list of state filenames

Return type:

list