AutoModel

Builds config and models automatically.

class multivae.models.AutoConfig

Class to reload any multivae.models configuration.

classmethod from_json_file(json_path)

Creates a BaseMultiVAEConfig instance from a JSON config file. It builds automatically the correct config for any multivae.models.

Parameters:

json_path (str) – The path to the json file containing all the parameters

Returns:

The created instance

Return type:

BaseMultiVAEConfig

class multivae.models.AutoModel

Utils class allowing to reload any multivae.models automatically.

classmethod load_from_folder(dir_path)

Class method to be used to load the model from a specific folder.

Parameters:

dir_path (str) – The path where the model should have been be saved.

Note

This function requires the folder to contain:

• a model_config.json and a model.pt if no custom architectures were provided

or

• a model_config.json, a model.pt and a encoders.pkl (resp. decoders.pkl) if a custom encoders (resp. decoders) were provided

classmethod load_from_hf_hub(hf_hub_path, allow_pickle=False)

Class method to be used to load a automaticaly a pretrained model from the Hugging Face hub.

Parameters:

hf_hub_path (str) – The path where the model should have been be saved on the hugginface hub.

Note

This function requires the folder to contain:

• a model_config.json and a model.pt if no custom architectures were provided

or

• a model_config.json, a model.pt and a encoder.pkl (resp. decoder.pkl) if a custom encoder (resp. decoder) was provided