datasets/datasets.py [211:236]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def download_mnist(self):
        """Skips download if cache is available"""
        train_set = torchvision.datasets.MNIST(
            "/tmp/",
            train=True,
            download=True,
            transform=transforms.Compose(
                [transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]
            ),
        )

        test_set = torchvision.datasets.MNIST(
            "/tmp/",
            train=False,
            download=True,
            transform=transforms.Compose(
                [transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]
            ),
        )

        (
            train_data,
            train_targets,
            valid_data,
            valid_targets,
        ) = ProjectiveMNIST.split_train_valid(train_set)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



datasets/datasets.py [323:348]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def download_mnist(self):
        """Skips download if cache is available"""
        train_set = torchvision.datasets.MNIST(
            "/tmp/",
            train=True,
            download=True,
            transform=transforms.Compose(
                [transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]
            ),
        )

        test_set = torchvision.datasets.MNIST(
            "/tmp/",
            train=False,
            download=True,
            transform=transforms.Compose(
                [transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]
            ),
        )

        (
            train_data,
            train_targets,
            valid_data,
            valid_targets,
        ) = ProjectiveMNIST.split_train_valid(train_set)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -