1、代码演示

embedding = nn.Embedding(10,3)
print(embedding)
input = torch.LongTensor([[1,2,3,4],[4,3,2,9]])
embedding(input)

2、构建Embeddings类来实现文本嵌入层

# 构建Embedding类来实现文本嵌入层
class Embeddings(nn.Module):
    def __init__(self,d_model,vocab):
        """
        :param d_model: 词嵌入的维度
        :param vocab: 词表的大小
        """
        super(Embeddings,self).__init__()
        self.lut = nn.Embedding(vocab,d_model)
        self.d_model = d_model
    def forward(self,x):
        """
        :param x: 因为Embedding层是首层，所以代表输入给模型的文本通过词汇映射后的张量
        :return:
        """
        return self.lut(x) * math.sqrt(self.d_model)

x = Variable(torch.LongTensor([[100,2,42,508],[491,998,1,221]]))
emb = Embeddings(512,1000)
embr = emb(x)
print(embr.shape)             # torch.Size([2, 4, 512])
print(embr)
print(embr[0][0].shape)       # torch.Size([512])