使用text_tokenizer + fit_text_tokenizer时,如何查看为每个文档创建的功能的标记?
我尝试了https://keras.rstudio.com/reference/text_tokenizer.html中显示的属性,但没有找到答案。
q_texts <- c('hi, how are you', 'fine, and you')
ktoken <- text_tokenizer( num_words = 5, filters = '', lower = FALSE ) %>% fit_text_tokenizer( q_texts )
在所示示例中,我希望以标记形式查看所有文档,例如: