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

Function Encoder

diff2flow/tiny_autoencoder.py:29–36  ·  view source on GitHub ↗
(latent_channels=4)

Source from the content-addressed store, hash-verified

27
28
29def Encoder(latent_channels=4):
30 return nn.Sequential(
31 conv(3, 64), Block(64, 64),
32 conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64),
33 conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64),
34 conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64),
35 conv(64, latent_channels),
36 )
37
38
39def Decoder(latent_channels=4):

Callers 1

__init__Method · 0.70

Calls 2

convFunction · 0.85
BlockClass · 0.85

Tested by

no test coverage detected