-
질문 & 답변
카테고리
-
세부 분야
자연어 처리
-
해결 여부
미해결
#@title Choose a BERT model to fine-tune
22.08.09 14:06 작성 조회수 216
0
"""
#@title Choose a BERT model to fine-tune
bert_model_name = 'bert_multi_cased_L-12_H-768_A-12' #@param ["bert_en_uncased_L-12_H-768_A-12", "bert_en_cased_L-12_H-768_A-12", "bert_multi_cased_L-12_H-768_A-12", "small_bert/bert_en_uncased_L-2_H-128_A-2", "small_bert/bert_en_uncased_L-2_H-256_A-4", "small_bert/bert_en_uncased_L-2_H-512_A-8", "small_bert/bert_en_uncased_L-2_H-768_A-12", "small_bert/bert_en_uncased_L-4_H-128_A-2", "small_bert/bert_en_uncased_L-4_H-256_A-4", "small_bert/bert_en_uncased_L-4_H-512_A-8", "small_bert/bert_en_uncased_L-4_H-768_A-12", "small_bert/bert_en_uncased_L-6_H-128_A-2", "small_bert/bert_en_uncased_L-6_H-256_A-4", "small_bert/bert_en_uncased_L-6_H-512_A-8", "small_bert/bert_en_uncased_L-6_H-768_A-12", "small_bert/bert_en_uncased_L-8_H-128_A-2", "small_bert/bert_en_uncased_L-8_H-256_A-4", "small_bert/bert_en_uncased_L-8_H-512_A-8", "small_bert/bert_en_uncased_L-8_H-768_A-12", "small_bert/bert_en_uncased_L-10_H-128_A-2", "small_bert/bert_en_uncased_L-10_H-256_A-4", "small_bert/bert_en_uncased_L-10_H-512_A-8", "small_bert/bert_en_uncased_L-10_H-768_A-12", "small_bert/bert_en_uncased_L-12_H-128_A-2", "small_bert/bert_en_uncased_L-12_H-256_A-4", "small_bert/bert_en_uncased_L-12_H-512_A-8", "small_bert/bert_en_uncased_L-12_H-768_A-12", "albert_en_base", "electra_small", "electra_base", "experts_pubmed", "experts_wiki_books", "talking-heads_base"]
map_name_to_handle = {
'bert_en_uncased_L-12_H-768_A-12':
'https://tfhub.dev/tensorflow/bert_en_uncased_L-12_H-768_A-12/3',
'bert_en_cased_L-12_H-768_A-12':
'https://tfhub.dev/tensorflow/bert_en_cased_L-12_H-768_A-12/3',
'bert_multi_cased_L-12_H-768_A-12':
'https://tfhub.dev/tensorflow/bert_multi_cased_L-12_H-768_A-12/3',
'small_bert/bert_en_uncased_L-2_H-128_A-2':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-2_H-128_A-2/1',
'small_bert/bert_en_uncased_L-2_H-256_A-4':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-2_H-256_A-4/1',
'small_bert/bert_en_uncased_L-2_H-512_A-8':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-2_H-512_A-8/1',
'small_bert/bert_en_uncased_L-2_H-768_A-12':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-2_H-768_A-12/1',
'small_bert/bert_en_uncased_L-4_H-128_A-2':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-4_H-128_A-2/1',
'small_bert/bert_en_uncased_L-4_H-256_A-4':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-4_H-256_A-4/1',
'small_bert/bert_en_uncased_L-4_H-512_A-8':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-4_H-512_A-8/1',
'small_bert/bert_en_uncased_L-4_H-768_A-12':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-4_H-768_A-12/1',
'small_bert/bert_en_uncased_L-6_H-128_A-2':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-6_H-128_A-2/1',
'small_bert/bert_en_uncased_L-6_H-256_A-4':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-6_H-256_A-4/1',
'small_bert/bert_en_uncased_L-6_H-512_A-8':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-6_H-512_A-8/1',
'small_bert/bert_en_uncased_L-6_H-768_A-12':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-6_H-768_A-12/1',
'small_bert/bert_en_uncased_L-8_H-128_A-2':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-8_H-128_A-2/1',
'small_bert/bert_en_uncased_L-8_H-256_A-4':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-8_H-256_A-4/1',
'small_bert/bert_en_uncased_L-8_H-512_A-8':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-8_H-512_A-8/1',
'small_bert/bert_en_uncased_L-8_H-768_A-12':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-8_H-768_A-12/1',
'small_bert/bert_en_uncased_L-10_H-128_A-2':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-10_H-128_A-2/1',
'small_bert/bert_en_uncased_L-10_H-256_A-4':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-10_H-256_A-4/1',
'small_bert/bert_en_uncased_L-10_H-512_A-8':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-10_H-512_A-8/1',
'small_bert/bert_en_uncased_L-10_H-768_A-12':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-10_H-768_A-12/1',
'small_bert/bert_en_uncased_L-12_H-128_A-2':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-12_H-128_A-2/1',
'small_bert/bert_en_uncased_L-12_H-256_A-4':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-12_H-256_A-4/1',
'small_bert/bert_en_uncased_L-12_H-512_A-8':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-12_H-512_A-8/1',
'small_bert/bert_en_uncased_L-12_H-768_A-12':
'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-12_H-768_A-12/1',
'albert_en_base':
'https://tfhub.dev/tensorflow/albert_en_base/2',
'electra_small':
'https://tfhub.dev/google/electra_small/2',
'electra_base':
'https://tfhub.dev/google/electra_base/2',
'experts_pubmed':
'https://tfhub.dev/google/experts/bert/pubmed/2',
'experts_wiki_books':
'https://tfhub.dev/google/experts/bert/wiki_books/2',
'talking-heads_base':
'https://tfhub.dev/tensorflow/talkheads_ggelu_bert_en_base/1',
}
map_model_to_preprocess = {
'bert_en_uncased_L-12_H-768_A-12':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'bert_en_cased_L-12_H-768_A-12':
'https://tfhub.dev/tensorflow/bert_en_cased_preprocess/3',
'small_bert/bert_en_uncased_L-2_H-128_A-2':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-2_H-256_A-4':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-2_H-512_A-8':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-2_H-768_A-12':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-4_H-128_A-2':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-4_H-256_A-4':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-4_H-512_A-8':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-4_H-768_A-12':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-6_H-128_A-2':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-6_H-256_A-4':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-6_H-512_A-8':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-6_H-768_A-12':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-8_H-128_A-2':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-8_H-256_A-4':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-8_H-512_A-8':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-8_H-768_A-12':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-10_H-128_A-2':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-10_H-256_A-4':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-10_H-512_A-8':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-10_H-768_A-12':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-12_H-128_A-2':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-12_H-256_A-4':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-12_H-512_A-8':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'small_bert/bert_en_uncased_L-12_H-768_A-12':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'bert_multi_cased_L-12_H-768_A-12':
'https://tfhub.dev/tensorflow/bert_multi_cased_preprocess/3',
'albert_en_base':
'https://tfhub.dev/tensorflow/albert_en_preprocess/3',
'electra_small':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'electra_base':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'experts_pubmed':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'experts_wiki_books':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
'talking-heads_base':
'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
}
tfhub_handle_encoder = map_name_to_handle[bert_model_name]
tfhub_handle_preprocess = map_model_to_preprocess[bert_model_name]
print(f'BERT model selected : {tfhub_handle_encoder}')
print(f'Preprocess model auto-selected: {tfhub_handle_preprocess}')
"""
이 부분에 토글 버튼이랑 밑에 코드들은 어디서 가져오나요??
텐서플로우 공식문서에는 토글 코드만 있고, 텐서플로우 허브에서도 코드를 가져올 수 있는 부분은 안보이는데
아무리 찾아도 안보여서 자세히 설명 부탁 드립니다ㅠㅠ
예제로 배우는 딥러닝 자연어 처리 입문 NLP with TensorFlow - RNN부터 BERT까지
실습 1 - BERT를 이용해서 IMDB Movie Review Dataset에 대한 Text Classification 해보기 (BERT 영어 Fine-Tuning)
강의실 바로가기
답변을 작성해보세요.
0
AISchool
지식공유자2022.08.19
안녕하세요~. 먼저 답신이 늦어서 죄송합니다ㅠ.
토글 버튼이랑 밑에 코드들을 어디서 가져온다는게 무슨 뜻인지 정확히 이해를 못하겠습니다ㅠㅠ.
공식 문서에서 소스 코드를 확인하고 싶으신거면 아래 그림에 [코드 표시] 버튼을 누르시면 됩니다.
좋은 하루되세요~.
감사합니다.
답변 1