MCPcopy Create free account
hub / github.com/CompVis/diff2flow / normalization

Function normalization

diff2flow/models/unet/util.py:101–107  ·  view source on GitHub ↗

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

(channels)

Source from the content-addressed store, hash-verified

99
100
101def normalization(channels):
102 """
103 Make a standard normalization layer.
104 :param channels: number of input channels.
105 :return: an nn.Module for normalization.
106 """
107 return GroupNorm32(32, channels)
108
109
110class GroupNorm32(nn.GroupNorm):

Callers 3

__init__Method · 0.90
__init__Method · 0.90
__init__Method · 0.90

Calls 1

GroupNorm32Class · 0.85

Tested by

no test coverage detected