MCPcopy Create free account
hub / github.com/baegwangbin/surface_normal_uncertainty / forward

Method forward

models/baseline.py:73–81  ·  view source on GitHub ↗
(self, features)

Source from the content-addressed store, hash-verified

71 self.conv3 = nn.Conv2d(128, num_classes, kernel_size=3, stride=1, padding=1)
72
73 def forward(self, features):
74 x_block0, x_block1, x_block2, x_block3, x_block4 = features[4], features[5], features[6], features[8], features[11]
75 x_d0 = self.conv2(x_block4)
76 x_d1 = self.up1(x_d0, x_block3)
77 x_d2 = self.up2(x_d1, x_block2)
78 x_d3 = self.up3(x_d2, x_block1)
79 x_d4 = self.up4(x_d3, x_block0)
80 out = self.conv3(x_d4)
81 return out
82
83
84if __name__ == '__main__':

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected