model_DeepCNN_MUI.py 文件源码

def forward(self, x):
        x_no_static = self.embed_no_static(x)
        # x_no_static = self.dropout(x_no_static)
        x_static = self.embed_static(x)
        # fix the embedding
        x_static = Variable(x_static.data)
        # x_static = self.dropout(x_static)
        x = torch.stack([x_static, x_no_static], 1)
        one_layer = x  # (N,W,D) #  torch.Size([64, 43, 300])
        # print("one_layer {}".format(one_layer.size()))
        # one_layer = self.dropout(one_layer)
        # one_layer = one_layer.unsqueeze(1)  # (N,Ci,W,D)  #  torch.Size([64, 1, 43, 300])
        # one layer
        one_layer = [torch.transpose(F.relu(conv(one_layer)).squeeze(3), 1, 2).unsqueeze(1) for conv in self.convs1] # torch.Size([64, 100, 36])
        # one_layer = [F.relu(conv(one_layer)).squeeze(3).unsqueeze(1) for conv in self.convs1] # torch.Size([64, 100, 36])
        # print(one_layer[0].size())
        # print(one_layer[1].size())
        # two layer
        two_layer = [F.relu(conv(one_layer)).squeeze(3) for (conv, one_layer) in zip(self.convs2, one_layer)]
        # print("two_layer {}".format(two_layer[0].size()))
        # print("two_layer {}".format(two_layer[1].size()))
        # pooling
        output = [F.max_pool1d(i, i.size(2)).squeeze(2) for i in two_layer]   #  torch.Size([64, 100]) torch.Size([64, 100])
        output = torch.cat(output, 1)  # torch.Size([64, 300])
        # dropout
        output = self.dropout(output)
        # linear
        output = self.fc1(output)
        logit = self.fc2(F.relu(output))
        return logit