原书出处
Natural Language Processing in Action, Second Edition
... def forward(self, x, hidden): #3 ... combined = torch.cat((x, hidden), axis=1) #4 ... hidden = self.W_c2h(combined) #5 ... y = self.W_c2y(combined) #6 ... y = self.softmax(y) ... return y, hidden #7 #1 vocab_size and hidden_size allocate space for the combined inputs. #2 Adds W_c2h1, W_c2h2, and so on “Linear” layers of the same size for deeper learning #3 “x” is a one-hot vector for
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-8.html
EPUB SHA-256:0e9a35e49ca446e322e5524e53f39fb6bee5b2b23d9cda10ef052aca770b0b36