MCPcopy Create free account
hub / github.com/ActiveVisionLab/DFNet / forward

Method forward

script/dm/pose_model.py:220–226  ·  view source on GitHub ↗
(self, Input)

Source from the content-addressed store, hash-verified

218 self.fc_pose = nn.Linear(1280, feat_dim)
219
220 def forward(self, Input):
221 x = self.feature_extractor(Input)
222 x = self.avgpool(x)
223 x = x.reshape(x.size(0), -1)
224 predict = self.fc_pose(x)
225 # pdb.set_trace()
226 return predict
227
228# PoseNet (SE(3)) w/ resnet34 backnone. We found dropout layer is unnecessary, so we set droprate as 0 in reported results.
229class PoseNet_res34(nn.Module):

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected