MCPcopy Create free account
hub / github.com/ICTMCG/FakeSV / forward

Method forward

code/models/Baselines.py:62–68  ·  view source on GitHub ↗
(self,  **kwargs)

Source from the content-addressed store, hash-verified

60 self.classifier = nn.Linear(fea_dim,2)
61
62 def forward(self, **kwargs):
63 frames=kwargs['frames']
64 fea_img = self.linear_img(frames)
65 fea_img = self.attention(fea_img)
66 fea_img = torch.mean(fea_img, -2)
67 output = self.classifier(fea_img)
68 return output
69
70class bVggish(torch.nn.Module):
71 def __init__(self,fea_dim):

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected