nip.scenario_base.pretrained_models

Base classes for dealing with pretrained models for transfer learning.

Pretrained models can by used to generate embeddings for datasets, which can then be used by agents instead of raw data. This means the agent starts with a good level of knowledge about the data.

This module contains the base class for pretrained models, as well as a registry for them.

Functions

get_pretrained_model_class(model_name, ...)	Get the class for a pretrained model by name.
register_pretrained_model_class(...)	Register a pretrained model class, so it can be built by name.

Classes

PretrainedModel(hyper_params, settings)

Base class for pretrained models, used to generate embeddings for datasets.