napari_cellseg3d.code_models.models.unet.buildingblocks

Functions

conv3d(in_channels, out_channels, ...)
create_conv(in_channels, out_channels, ...)	Create a list of modules with together constitute a single conv layer with non-linearity and optional batchnorm/groupnorm.
create_decoders(f_maps, basic_module, ...)
create_encoders(in_channels, f_maps, ...)

Classes

AbstractUpsampling(upsample)	Abstract class for upsampling.
Decoder(in_channels, out_channels[, ...])	A single module for decoder path consisting of the upsampling layer (either learned ConvTranspose3d or nearest neighbor interpolation) followed by a basic module (DoubleConv or ExtResNetBlock). :param in_channels: number of input channels :type in_channels: int :param out_channels: number of output channels :type out_channels: int :param conv_kernel_size: size of the convolving kernel :type conv_kernel_size: int or tuple :param scale_factor: used as the multiplier for the image H/W/D in case of nn.Upsample or as stride in case of ConvTranspose3d, must reverse the MaxPool3d operation from the corresponding encoder :type scale_factor: tuple :param basic_module: either ResNetBlock or DoubleConv :type basic_module: nn.Module :param conv_layer_order: determines the order of layers in DoubleConv module. See DoubleConv for more info. :type conv_layer_order: string :param num_groups: number of groups for the GroupNorm :type num_groups: int :param padding: add zero-padding added to all three sides of the input :type padding: int or tuple :param upsample: should the input be upsampled :type upsample: boole.
DoubleConv(in_channels, out_channels, encoder)	A module consisting of two consecutive convolution layers (e.g. BatchNorm3d+ReLU+Conv3d).
Encoder(in_channels, out_channels[, ...])	A single module from the encoder path consisting of the optional max pooling layer (one may specify the MaxPool kernel_size to be different than the standard (2,2,2), e.g. if the volumetric data is anisotropic (make sure to use complementary scale_factor in the decoder path) followed by a DoubleConv module. :param in_channels: number of input channels :type in_channels: int :param out_channels: number of output channels :type out_channels: int :param conv_kernel_size: size of the convolving kernel :type conv_kernel_size: int or tuple :param apply_pooling: if True use MaxPool3d before DoubleConv :type apply_pooling: bool :param pool_kernel_size: the size of the window :type pool_kernel_size: int or tuple :param pool_type: pooling layer: 'max' or 'avg' :type pool_type: str :param basic_module: either ResNetBlock or DoubleConv :type basic_module: nn.Module :param conv_layer_order: determines the order of layers in DoubleConv module. See DoubleConv for more info. :type conv_layer_order: string :param num_groups: number of groups for the GroupNorm :type num_groups: int :param padding: add zero-padding added to all three sides of the input :type padding: int or tuple.
ExtResNetBlock(in_channels, out_channels[, ...])	Basic UNet block consisting of a SingleConv followed by the residual block.
InterpolateUpsampling([mode])
NoUpsampling()	Initialize internal Module state, shared by both nn.Module and ScriptModule.
SingleConv(in_channels, out_channels[, ...])	Basic convolutional module consisting of a Conv3d, non-linearity and optional batchnorm/groupnorm.
TransposeConvUpsampling([in_channels, ...])