445e7e0b74495326ef6f90f238d16513a437d797,test/retiarii_test/mnasnet/test.py,,,#,14

Before Change

    base_model = MNASNet(0.5, _DEFAULT_DEPTHS, _DEFAULT_CONVOPS, _DEFAULT_KERNEL_SIZES,
                         _DEFAULT_NUM_LAYERS, _DEFAULT_SKIPS)
    trainer = PyTorchImageClassificationTrainer(base_model, dataset_cls="CIFAR10",
                                                dataset_kwargs={"root": "data/cifar10", "download": True},
                                                dataloader_kwargs={"batch_size": 32},
                                                optimizer_kwargs={"lr": 1e-3},
                                                trainer_kwargs={"max_epochs": 1})

    // new interface
    applied_mutators = []
    applied_mutators.append(BlockMutator("mutable_0"))

After Change

    base_model = MNASNet(0.5, _DEFAULT_DEPTHS, _DEFAULT_CONVOPS, _DEFAULT_KERNEL_SIZES,
                         _DEFAULT_NUM_LAYERS, _DEFAULT_SKIPS)

    train_transform = transforms.Compose([
        transforms.RandomCrop(32, padding=4),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
    ])
    valid_transform = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
    ])
    train_dataset = bm(CIFAR10)(root="data/cifar10", train=True, download=True, transform=train_transform)
    test_dataset = bm(CIFAR10)(root="data/cifar10", train=False, download=True, transform=valid_transform)
    trainer = pl.Classification(train_dataloader=pl.DataLoader(train_dataset, batch_size=100),
                                val_dataloaders=pl.DataLoader(test_dataset, batch_size=100),
                                max_epochs=1, limit_train_batches=0.2)

    applied_mutators = [
        BlockMutator("mutable_0"),
        BlockMutator("mutable_1")

Instances