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

Function Normalize

diff2flow/models/unet/attention.py:86–87  ·  view source on GitHub ↗
(in_channels)

Source from the content-addressed store, hash-verified

84
85
86def Normalize(in_channels):
87 return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)
88
89
90class SpatialSelfAttention(nn.Module):

Callers 2

__init__Method · 0.70
__init__Method · 0.70

Calls

no outgoing calls

Tested by

no test coverage detected