- This topic has 1 reply, 2 voices, and was last updated 3 years, 10 months ago by .
Viewing 2 posts - 1 through 2 (of 2 total)
Viewing 2 posts - 1 through 2 (of 2 total)
- You must be logged in to reply to this topic.
Home › Forums › Fórum Processamento de Linguagem Natural com Deep Learning › ARQUITETURA TRANSFORMER
Tagged: Tokenização
Boa aNoite
Solicito auxilio para corrigir o erro destacado abaixo quando executo o comando contido no material do curso
COMANDO : tokenizer_en = tfds.features.text.SubwordTextEncoder.build_from_corpus(corpus_en, target_vocab_size=2**13)
ERRO : AttributeError: module ‘tensorflow_datasets.core.features’ has no attribute ‘text’
Atenciosamente
No Aguardo
Atte.,
Roberto Figueiredo de Paula
Engenheiro de Software
Olá Roberto, utilize o comando abaixo:
tokenizer_en = tfds.deprecated.text.SubwordTextEncoder.build_from_corpus(corpus_en, target_vocab_size=2**13)
Fabio