自作データで学習したモデルを再度読み込んで2回目の学習を実行[Flair]
自作データを使って2回以上の学習を回したときにハマったのでまとめる．
筆者が自作データでNERの学習を行なったときに，1回目に学習したモデルを2回目の学習に引き継ぎたいと思った．
しかしながら，その方法は公式ドキュメントには書いていなかったので，自分で調べて解決した．
結論としては，SequenceTagger.load()を使って，1回目のモデルを読み込み，それをtaggerとして用いた．
以下，1回目に学習したモデルを2回目の学習に引き継ぐコード．
from flair.data import Corpus from flair.embeddings import TokenEmbeddings, WordEmbeddings, StackedEmbeddings from flair.data import Sentence from flair.models import SequenceTagger from flair.embeddings import ( WordEmbeddings, CharacterEmbeddings, FlairEmbeddings, BertEmbeddings, ) from flair.data import Corpus from flair.datasets import ColumnCorpus from typing import List from pathlib import Path import sys from docopt import docopt def loadCorpus(data_folder): # define columns columns = {0: "text", 1: "ner"} # init a corpus using column format, data folder and the names of the train, dev and test files corpus: Corpus = ColumnCorpus( data_folder, columns, train_file="train.tsv", test_file="test.tsv", dev_file="devel.tsv", ) return corpus # 1回目の学習 datapath = "/root/data/input/my-ner-data/" # 1. get the corpus corpus: Corpus = loadCorpus(datapath) print(corpus) # 2. what tag do we want to predict? tag_type = "ner" # 3. make the tag dictionary from the corpus tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type) print(tag_dictionary.idx2item) # 4. initialize embeddings embedding_objects: List[TokenEmbeddings] = [] embedding_objects.append(CharacterEmbeddings()) embeddings: StackedEmbeddings = StackedEmbeddings(embeddings=embedding_objects) # 5. initialize sequence tagger tagger: SequenceTagger = SequenceTagger( hidden_size=256, embeddings=embeddings, tag_dictionary=tag_dictionary, tag_type=tag_type, use_crf=True, ) # 6. initialize trainer from flair.trainers import ModelTrainer resultpath = "/root/output/flair_test" trainer: ModelTrainer = ModelTrainer(tagger, corpus) # 7. start training resultpath = Path(resultpath) / "tagger_results" / "char" trainer.train( str(resultpath), learning_rate=0.1, mini_batch_size=32, max_epochs=5, patience=5 ) # 2回目の学習 best_model = "/root/output/flair_test/tagger_results/char/best-model.pt" # 1. get the corpus corpus: Corpus = loadCorpus(datapath) print(corpus) # 2. what tag do we want to predict? tag_type = "ner" # 3. make the tag dictionary from the corpus tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type) print(tag_dictionary.idx2item) # 4. initialize embeddings embedding_objects: List[TokenEmbeddings] = [] embedding_objects.append(CharacterEmbeddings()) embeddings: StackedEmbeddings = StackedEmbeddings(embeddings=embedding_objects) # 5. initialize sequence tagger # tagger: SequenceTagger = SequenceTagger( # hidden_size=256, # embeddings=embeddings, # tag_dictionary=tag_dictionary, # tag_type=tag_type, # use_crf=True, # ) # 2回目のtaggerは，SequenceTagger.loadで読み込んだモデルを使う． tagger = SequenceTagger.load(best_model) # 6. initialize trainer from flair.trainers import ModelTrainer resultpath = "/root/output/flair_test" trainer: ModelTrainer = ModelTrainer(tagger, corpus) # 7. start training resultpath = Path(resultpath) / "tagger_results" / "char" trainer.train( str(resultpath), learning_rate=0.1, mini_batch_size=32, max_epochs=5, patience=5 )