每日提升一点点

MAX_VOCAB_SIZE = 10000 UNK, PAD = '<UNK>', '<PAD>' def build_vocab(file_name, tokenize, max_size, min_freq): vocab_dic = {} with open(file_name, 'r', encoding='utf-8') as f: for line in f: lin = line.strip() .

Embedding 模块作用：将词的索引转化为词对应的词向量，需要我们设置的两个参数：词汇表的大小和词嵌入的维度。 num_embeddings (int): size of the dictionary of embeddings embedding_dim (int): the size of each embedding vector import torch.nn as nn import torch embedding = nn.Embedding(10, 3) string = 'hell