Function Normalize

sat/sgm/modules/attention.py:114–115 · view source on GitHub ↗

(in_channels)

Source from the content-addressed store, hash-verified

112
113
114	def Normalize(in_channels):
115	return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)
116
117
118	class LinearAttention(nn.Module):

__init__Method · 0.70

no outgoing calls

no test coverage detected