locpix.img_processing.models.unet#

UNET model

Adapted from milesial/Pytorch-UNet

Classes

DoubleConv(in_channels, out_channels[, ...])

(convolution => [BN] => ReLU) * 2

Down(in_channels, out_channels)

Downscaling with maxpool then double conv

OutConv(in_channels, out_channels)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Up(in_channels, out_channels[, bilinear])

Upscaling then double conv

two_d_UNet(n_channels, n_classes[, bilinear])

Initialize internal Module state, shared by both nn.Module and ScriptModule.