Making Predictions¶
After completing a training session, use the new or updated federated model to make predictions.
You can load the model as an object. For example:
model = hfl_session.model()
model.predict('test.parquet')
Alternatively, you can load the HFL model as a standard pytorch
or sklearn
object, and then make predictions using the same methods as you would in pytorch or sklearn. For example:
model.as_pytorch()
or
model.as_sklearn()
The prediction output is saved as file under the same directory as the input data with the file name <\original_input_file_name>_<\timestamp>.