def transforms()

in src/controlnet_aux/zoe/zoedepth/models/base_models/midas_repo/hubconf.py [0:0]
125 lines of code
1 McCabe index (conditional complexity)

def transforms():
    import cv2
    from torchvision.transforms import Compose
    from midas.transforms import Resize, NormalizeImage, PrepareForNet
    from midas import transforms

    transforms.default_transform = Compose(
        [
            lambda img: {"image": img / 255.0},
            Resize(
                384,
                384,
                resize_target=None,
                keep_aspect_ratio=True,
                ensure_multiple_of=32,
                resize_method="upper_bound",
                image_interpolation_method=cv2.INTER_CUBIC,
            ),
            NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
            PrepareForNet(),
            lambda sample: torch.from_numpy(sample["image"]).unsqueeze(0),
        ]
    )

    transforms.small_transform = Compose(
        [
            lambda img: {"image": img / 255.0},
            Resize(
                256,
                256,
                resize_target=None,
                keep_aspect_ratio=True,
                ensure_multiple_of=32,
                resize_method="upper_bound",
                image_interpolation_method=cv2.INTER_CUBIC,
            ),
            NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
            PrepareForNet(),
            lambda sample: torch.from_numpy(sample["image"]).unsqueeze(0),
        ]
    )

    transforms.dpt_transform = Compose(
        [
            lambda img: {"image": img / 255.0},
            Resize(
                384,
                384,
                resize_target=None,
                keep_aspect_ratio=True,
                ensure_multiple_of=32,
                resize_method="minimal",
                image_interpolation_method=cv2.INTER_CUBIC,
            ),
            NormalizeImage(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
            PrepareForNet(),
            lambda sample: torch.from_numpy(sample["image"]).unsqueeze(0),
        ]
    )

    transforms.beit512_transform = Compose(
        [
            lambda img: {"image": img / 255.0},
            Resize(
                512,
                512,
                resize_target=None,
                keep_aspect_ratio=True,
                ensure_multiple_of=32,
                resize_method="minimal",
                image_interpolation_method=cv2.INTER_CUBIC,
            ),
            NormalizeImage(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
            PrepareForNet(),
            lambda sample: torch.from_numpy(sample["image"]).unsqueeze(0),
        ]
    )

    transforms.swin384_transform = Compose(
        [
            lambda img: {"image": img / 255.0},
            Resize(
                384,
                384,
                resize_target=None,
                keep_aspect_ratio=False,
                ensure_multiple_of=32,
                resize_method="minimal",
                image_interpolation_method=cv2.INTER_CUBIC,
            ),
            NormalizeImage(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
            PrepareForNet(),
            lambda sample: torch.from_numpy(sample["image"]).unsqueeze(0),
        ]
    )

    transforms.swin256_transform = Compose(
        [
            lambda img: {"image": img / 255.0},
            Resize(
                256,
                256,
                resize_target=None,
                keep_aspect_ratio=False,
                ensure_multiple_of=32,
                resize_method="minimal",
                image_interpolation_method=cv2.INTER_CUBIC,
            ),
            NormalizeImage(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
            PrepareForNet(),
            lambda sample: torch.from_numpy(sample["image"]).unsqueeze(0),
        ]
    )

    transforms.levit_transform = Compose(
        [
            lambda img: {"image": img / 255.0},
            Resize(
                224,
                224,
                resize_target=None,
                keep_aspect_ratio=False,
                ensure_multiple_of=32,
                resize_method="minimal",
                image_interpolation_method=cv2.INTER_CUBIC,
            ),
            NormalizeImage(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
            PrepareForNet(),
            lambda sample: torch.from_numpy(sample["image"]).unsqueeze(0),
        ]
    )

    return transforms