Args: spatial_dims: number of spatial dimensions. in_chns: number of input channels. out_chns: number of output channels. act: activation type and arguments. norm: feature normalization type and arguments. bias: whether
(
self,
spatial_dims: int,
in_chns: int,
out_chns: int,
act: str | tuple,
norm: str | tuple,
bias: bool,
dropout: float | tuple = 0.0,
)
| 61 | """maxpooling downsampling and two convolutions.""" |
| 62 | |
| 63 | def __init__( |
| 64 | self, |
| 65 | spatial_dims: int, |
| 66 | in_chns: int, |
| 67 | out_chns: int, |
| 68 | act: str | tuple, |
| 69 | norm: str | tuple, |
| 70 | bias: bool, |
| 71 | dropout: float | tuple = 0.0, |
| 72 | ): |
| 73 | """ |
| 74 | Args: |
| 75 | spatial_dims: number of spatial dimensions. |
| 76 | in_chns: number of input channels. |
| 77 | out_chns: number of output channels. |
| 78 | act: activation type and arguments. |
| 79 | norm: feature normalization type and arguments. |
| 80 | bias: whether to have a bias term in convolution blocks. |
| 81 | dropout: dropout ratio. Defaults to no dropout. |
| 82 | |
| 83 | """ |
| 84 | super().__init__() |
| 85 | max_pooling = Pool["MAX", spatial_dims](kernel_size=2) |
| 86 | convs = TwoConv(spatial_dims, in_chns, out_chns, act, norm, bias, dropout) |
| 87 | self.add_module("max_pooling", max_pooling) |
| 88 | self.add_module("convs", convs) |
| 89 | |
| 90 | |
| 91 | class UpCat(nn.Module): |