Question About The Model

[18pxrsun]

Hello, I noticed that there are two layers:self. kb and self. kc is not used in your model code , so I annotated them.However, the fscore dropped after annotation. Do you know why?
self.att = SelfAttention(input_size=self.m, output_size=self.m)
self.ka = nn.Linear(in_features=self.m, out_features=1024)
self.kb = nn.Linear(in_features=self.ka.out_features, out_features=1024)
self.kc = nn.Linear(in_features=self.kb.out_features, out_features=1024)
self.kd = nn.Linear(in_features=self.ka.out_features, out_features=1)

[ok1zjf]

Hi, to be honest I don't know. The layers are, indeed, not used so commenting them out should not affect the
performance. I had tried it last night but the results were ok. But this test was done with different version of python, pytorch
and other libs. Perhaps there is a bug in the pytorch?