MONAI Tranform - Debugging & Error

[agokli]

I have following MONAI Transform:

train_transform = Compose(
[

    LoadImaged(keys=["image", "label"]),
    EnsureChannelFirstd(keys="image"),
    EnsureTyped(keys=["image", "label"]),
    Orientationd(keys=["image", "label"], axcodes="RAS"),
    Spacingd(
        keys=["image", "label"],
        pixdim=(1.0, 1.0, 1.0),
        mode=("bilinear", "nearest"),
    ),
    # Resize to a larger size before cropping
    Resized(keys=["image", "label"], spatial_size=[128, 128, 128], mode=("trilinear", "nearest")),
    # Use CenterSpatialCropd instead of RandSpatialCropd
    CenterSpatialCropd(keys=["image", "label"], roi_size=[64, 64, 64]), 
    RandFlipd(keys=["image", "label"], prob=0.5, spatial_axis=0),
    RandFlipd(keys=["image", "label"], prob=0.5, spatial_axis=1),
    RandFlipd(keys=["image", "label"], prob=0.5, spatial_axis=2),
    NormalizeIntensityd(keys="image", nonzero=True, channel_wise=True),
    RandScaleIntensityd(keys="image", factors=0.1, prob=1.0),
    RandShiftIntensityd(keys="image", offsets=0.1, prob=1.0),
]

)

I am running trying to run model for "RSNA-MICCAI Brain Tumor Radiogenomic Classification" and receiving following errror:

RuntimeError: input image (T: 1 H: 32 W: 24) smaller than kernel size (kT: 2 kH: 2 kW: 2)

Can you please explain the cause(s) for above error and potential solution(s) . I tried to change spatial_size attribute (Resized). I will like to understand how to diagnose MONAI Transform.

Thanks

[KumoLiu]

Hi @agokli, if you're working with 2D data, please ensure you're using a 2D kernel as well.