Save_load

Tmp saving and loading.

the_utils.save_load.save_model(model_filename: str, model: Module, optimizer: Optimizer, current_epoch: int, loss: float) → None

Save model, optimizer, current_epoch, loss to .checkpoints/${model_filename}.pt.

Parameters:

• model_filename (str) – filename to save model.

• model (torch.nn.Module) – model.

• optimizer (torch.optim.Optimizer) – optimizer.

• current_epoch (int) – current epoch.

• loss (float) – loss.

the_utils.save_load.load_model(model_filename: str, model: Module, optimizer: Optimizer | None = None, device: device = device(type='cpu')) → Tuple[Module, Optimizer, int, float]

Load model from .checkpoints/${model_filename}.pt.

Parameters:

• model_filename (str) – filename to load model.

• model (torch.nn.Module) – model.

• optimizer (torch.optim.Optimizer) – optimizer.

Returns:

[model, optimizer, epoch, loss]

Return type:

Tuple[torch.nn.Module, torch.optim.Optimizer, int, float]

the_utils.save_load.save_embedding(node_embeddings: tensor, dataset_name: str, model_name: str, params: dict, save_dir: str = './save', verbose: bool | int = True)

Save embeddings.

Parameters:

• node_embeddings (torch.tensor) – node embeddings.

• dataset_name (str) – dataset name.

• model_name (str) – model name.

• params (dict) – parameter dict.

• save_dir (str, optional) – save dir. Defaults to “./save”.

• verbose (Union[bool, int], optional) – whether to print debug info. Defaults to True.