View all Poutyne analysis

How to use the poutyne.numpy_to_torch function in Poutyne

To help you get started, we’ve selected a few Poutyne examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

GRAAL-Research / poutyne / poutyne / framework / model.py View on Github

def _dataloader_from_data(self, args, batch_size):
        args = numpy_to_torch(args)
        dataset = TensorDataset(*args) if len(args) > 1 else args[0]
        generator = DataLoader(dataset, batch_size)
        return generator

GRAAL-Research / poutyne / poutyne / framework / model.py View on Github

def _process_input(self, *args):
        args = numpy_to_torch(args)
        if self.device is not None:
            args = torch_to(args, self.device)
        return args[0] if len(args) == 1 else args