vathos.model.resunetΒΆ
Residual - Unet - Enhanced
-
class
ResDoubleConv
(in_channels, out_channels)[source]ΒΆ Basic DoubleConv of a ResNetV2
Performs basic Pre Activated ResNet Double Convolution
Parameters: - in_channels β input channels
- out_channels β output channels
-
class
ResDownBlock
(in_channels, out_channels)[source]ΒΆ Basic DownBlock of a ResNetV2
Performs a Residual Down operation
Parameters: - in_channels β input channels
- out_channels β output channels
output: \((N, C, H/2, W/2)\)
-
class
ResUpBlock
(in_channels, out_channels, skip_channels, dense_channels=None)[source]ΒΆ Basic UpBlock of a ResNetV2
Performs Residual Up Convolution on the input, uses PixelShuffle to produce checkerboard-free outputs
Parameters: - in_channels β input channels
- out_channels β output channels
- skip_channels β skip input channels
- dense_channels β dense input channels (from another decoder)
Note
The input is applied with a 1x1 convolution and then pixel shuffle to keep the channels constant and also produce checkerboard-free outputs, the rest is then followed by double convolution