Open kuangdai opened 6 months ago
Can you maybe add this feature, please?
I think the main change would be
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, ):
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.
Hi, @kuangdai. Please feel free to open the PR!
If kernel_size can accept a tuple, doesn't it mean that padding should also accept a tuple?
kernel_size
padding
Can you maybe add this feature, please?
I think the main change would be
I can create a PR if you prefer this way.