PyTorch toolbox to work with spherical surfaces.

Note

This page is a reference documentation. It only explains the class signature, and not how to use it. Please refer to the gallery for the big picture.

class surfify.models.unet.DownGBlock(in_ch, out_ch, first=False)[source]¶

Downsampling block in grided spherical UNet: max pooling => (conv => BN => ReLU) * 2

__init__(in_ch, out_ch, first=False)[source]¶

Init DownGBlock.

Parameters

in_ch : int

input features/channels.

out_ch : int

output features/channels.

first : bool, default False

if set skip the pooling block.