Different kernel sizes for different dimensions

[kuangdai]

Can you maybe add this feature, please?

I think the main change would be

• From

class ConvolutionalBlock(nn.Module):
    def __init__(
            self,
            dimensions: int,
            in_channels: int,
            out_channels: int,
            normalization: Optional[str] = None,
            kernel_size: int = 3,
            activation: Optional[str] = 'ReLU',
            preactivation: bool = False,
            padding: int = 0,
            padding_mode: str = 'zeros',
            dilation: Optional[int] = None,
            dropout: float = 0,
            ):

• To

class ConvolutionalBlock(nn.Module):
    def __init__(
            self,
            dimensions: int,
            in_channels: int,
            out_channels: int,
            normalization: Optional[str] = None,
            kernel_size: int = Union[int, Sequence[int]],
            activation: Optional[str] = 'ReLU',
            preactivation: bool = False,
            padding: int = 0,
            padding_mode: str = 'zeros',
            dilation: Optional[int] = None,
            dropout: float = 0,
            ):

I can create a PR if you prefer this way.

[fepegar]

Hi, @kuangdai. Please feel free to open the PR!

[lizhuoq]

If kernel_size can accept a tuple, doesn't it mean that padding should also accept a tuple?