pytorch学习笔记-----RNN CNN自然语言处理

 RNN 

class Model(nn.Module):
    def __init__(self,config):
        super(Model,self).__init__()
        self.embedding=nn.Embedding.from_pretrained(config.embedding_pretrained,freeze=False)
        self.lstm=nn.LSTM(config.embed,config.hidden_size,config.num_layers,bidirectional=True,batch_first=True,dropout=config.dropout)
        #词向量，隐层数量，层数，是否双向，第一维度是否为batchsize,dropout
        self.fc=nn.Linear(config.hidden_size*2,config.num_classes)
    def forward(self,x):
        x,_=x
        out=self.embedding(x)
        out=self.lstm(out)
        out=self.fc(out[:,-1,:])
        return out

 

 CNN

class Model(nn.Module):
    def __init__(self,config):
        super(Model,self).__init__()
        self.embedding=nn.Embedding.from_pretrained(config.embedding_pretrained,freeze=False)
        self.convs=nn.ModuleList(
            [nn.Conv2d(1,config.num_filters,(k,config.embed)for k in config.filter_size)]
        )
        self.dropout=nn.Dropout(config.dropout)
        self.fc=nn.Linear(config.num_filters*len(config.filter_size),config.num_classes)
    def conv_and_pool(self,x,conv):
        x=F.relu(conv(x)).squeeze(3)
        x=F.max_pool1d(x,x.size(2).squeeze)
    def forward(self,x):
        out=self.embedding(x[0])
        out=out.unsqueeze(1)
        out=torch.cat([self.conv_and_pool(out,conv)for conv in self.convs ],1)
        out=self.dropout(out)
        out=self.fc(out)
        return out