export_latents

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

Export predicted latents using an already initialized data_generator and model.

Latents are saved based on the model’s hparams dict unless another file is provided. The default filename is [lab_id]_[expt_id]_[animal_id]_[session_id]_latents.pkl.

Parameters:

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

  • model (AE object) – pytorch model

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

Returns:

list of latent filenames

Return type:

list