Layers

Layer module.

This submodule contains layers used in the CAREamics models.

`Conv_Block`

Bases: Module

Convolution block used in UNets.

Convolution block consist of two convolution layers with optional batch norm, dropout and with a final activation function.

The parameters are directly mapped to PyTorch Conv2D and Conv3d parameters, see PyTorch torch.nn.Conv2d and torch.nn.Conv3d for more information.

Parameters:

Name	Type	Description	Default
`conv_dim`	`int`	Number of dimension of the convolutions, 2 or 3.	required
`in_channels`	`int`	Number of input channels.	required
`out_channels`	`int`	Number of output channels.	required
`intermediate_channel_multiplier`	`int`	Multiplied for the number of output channels, by default 1.	`1`
`stride`	`int`	Stride of the convolutions, by default 1.	`1`
`padding`	`int`	Padding of the convolutions, by default 1.	`1`
`bias`	`bool`	Bias of the convolutions, by default True.	`True`
`groups`	`int`	Controls the connections between inputs and outputs, by default 1.	`1`
`activation`	`str`	Activation function, by default "ReLU".	`'ReLU'`
`dropout_perc`	`float`	Dropout percentage, by default 0.	`0`
`use_batch_norm`	`bool`	Use batch norm, by default False.	`False`

`forward(x)`

Forward pass.

Parameters:

Name	Type	Description	Default
`x`	`Tensor`	Input tensor.	required

Returns:

Type	Description
`Tensor`	Output tensor.

`MaxBlurPool`

Bases: Module

Compute pools and blurs and downsample a given feature map.

Inspired by Kornia MaxBlurPool implementation. Equivalent to nn.Sequential(nn.MaxPool2d(...), BlurPool2D(...))

Parameters

dim : int Toggles between 2D and 3D. kernel_size : Union[tuple[int, int], int] Kernel size for max pooling. stride : int Stride for pooling. max_pool_size : int Max kernel size for max pooling. ceil_mode : bool Ceil mode, by default False. Set to True to match output size of conv2d.

`forward(x)`

Forward pass of the function.

Parameters:

Name	Type	Description	Default
`x`	`Tensor`	Input tensor.	required

Returns:

Type	Description
`Tensor`	Output tensor.

`get_pascal_kernel_1d(kernel_size, norm=False, *, device=None, dtype=None)`

Generate Yang Hui triangle (Pascal's triangle) for a given number.

Inspired by Kornia implementation. TODO link

Parameters:

Name	Type	Description	Default
`kernel_size`	`int`	Kernel size.	required
`norm`	`bool`	Normalize the kernel, by default False.	`False`
`device`	`Optional[device]`	Device of the tensor, by default None.	`None`
`dtype`	`Optional[dtype]`	Data type of the tensor, by default None.	`None`

Returns:

Type	Description
`Tensor`	Pascal kernel.

Examples:

>>> get_pascal_kernel_1d(1)
tensor([1.])
>>> get_pascal_kernel_1d(2)
tensor([1., 1.])
>>> get_pascal_kernel_1d(3)
tensor([1., 2., 1.])
>>> get_pascal_kernel_1d(4)
tensor([1., 3., 3., 1.])
>>> get_pascal_kernel_1d(5)
tensor([1., 4., 6., 4., 1.])
>>> get_pascal_kernel_1d(6)
tensor([ 1.,  5., 10., 10.,  5.,  1.])