pytorch中的embedding词向量的使用方法

import torch
from torch import nn
from torch.autograd import Variable
# 定义词嵌入
embeds = nn.Embedding(2, 5) # 2 个单词，维度 5
# 得到词嵌入矩阵,开始是随机初始化的
torch.manual_seed(1)
embeds.weight
# 输出结果：
Parameter containing:
-0.8923 -0.0583 -0.1955 -0.9656 0.4224
 0.2673 -0.4212 -0.5107 -1.5727 -0.1232
[torch.FloatTensor of size 2x5]

pretrained_weight = np.array(args.pretrained_weight) # 已有词向量的numpy
self.embed.weight.data.copy_(torch.from_numpy(pretrained_weight))

# 访问第 50 个词的词向量
embeds = nn.Embedding(100, 10)
embeds(Variable(torch.LongTensor([50])))
# 输出：
Variable containing:
 0.6353 1.0526 1.2452 -1.8745 -0.1069 0.1979 0.4298 -0.3652 -0.7078 0.2642
[torch.FloatTensor of size 1x10]

Input: LongTensor (N, W), N = mini-batch, W = number of indices to extract per mini-batch
Output: (N, W, embedding_dim)

# an Embedding module containing 10 tensors of size 3
embedding = nn.Embedding(10, 3)
# 每批取两组，每组四个单词
input = Variable(torch.LongTensor([[1,2,4,5],[4,3,2,9]]))
a = embedding(input) # 输出2*4*3
a[0],a[1]

(Variable containing:
 -1.2603 0.4337 0.4181
 0.4458 -0.1987 0.4971
 -0.5783 1.3640 0.7588
 0.4956 -0.2379 -0.7678
 [torch.FloatTensor of size 4x3], Variable containing:
 -0.5783 1.3640 0.7588
 -0.5313 -0.3886 -0.6110
 0.4458 -0.1987 0.4971
 -1.3768 1.7323 0.4816
 [torch.FloatTensor of size 4x3])