hookeai.material_model_finder.model.material_discovery.data_scaler_transform

data_scaler_transform(model, tensor, features_type, mode='normalize')

Perform data scaling operation on features PyTorch tensor.

Parameters:

• model (torch.nn.Module) – Model.

• tensor (torch.Tensor) – Features PyTorch tensor.

• features_type (str) –

  Features for which data scaler is required:

  ’features_in’ : Input features

  ’features_out’ : Output features

• mode ({'normalize', 'denormalize'}, default=normalize) – Data scaling transformation type.

Returns:

transformed_tensor – Transformed features PyTorch tensor.

Return type:

torch.Tensor