def test_train_resume_sequence_tagging_training(results_base_path, tasks_base_path):
corpus_1 = flair.datasets.ColumnCorpus(
data_folder=tasks_base_path / "fashion", column_format={0: "text", 2: "ner"}
)
corpus_2 = flair.datasets.GERMEVAL(base_path=tasks_base_path)
corpus = MultiCorpus([corpus_1, corpus_2])
tag_dictionary = corpus.make_tag_dictionary("ner")
embeddings = WordEmbeddings("turian")
model: SequenceTagger = SequenceTagger(
hidden_size=64,
embeddings=embeddings,
tag_dictionary=tag_dictionary,
tag_type="ner",
use_crf=False,
)
trainer = ModelTrainer(model, corpus)
trainer.train(results_base_path, max_epochs=2, shuffle=False, checkpoint=True)
checkpoint = SequenceTagger.load_checkpoint(results_base_path / "checkpoint.pt")
trainer = ModelTrainer.load_from_checkpoint(checkpoint, corpus)
trainer.train(results_base_path, max_epochs=2, shuffle=False, checkpoint=True)
# clean up results directory
shutil.rmtree(results_base_path)
def test_train_resume_text_classification_training(results_base_path,
tasks_base_path):
corpus = flair.datasets.ClassificationCorpus(tasks_base_path / "imdb")
label_dict = corpus.make_label_dictionary()
embeddings: TokenEmbeddings = FlairEmbeddings("news-forward-fast",
use_cache=False)
document_embeddings: DocumentRNNEmbeddings = DocumentRNNEmbeddings(
[embeddings], 128, 1, False)
model = TextClassifier(document_embeddings, label_dict, False)
trainer = ModelTrainer(model, corpus)
trainer.train(results_base_path,
max_epochs=2,
shuffle=False,
checkpoint=True)
checkpoint = TextClassifier.load_checkpoint(results_base_path /
"checkpoint.pt")
trainer = ModelTrainer.load_from_checkpoint(checkpoint, corpus)
trainer.train(results_base_path,
max_epochs=2,
shuffle=False,
checkpoint=True)
# clean up results directory
shutil.rmtree(results_base_path)
def test_train_resume_text_classification_training(results_base_path,
tasks_base_path):
corpus = NLPTaskDataFetcher.load_corpus('imdb', base_path=tasks_base_path)
label_dict = corpus.make_label_dictionary()
embeddings: TokenEmbeddings = FlairEmbeddings('news-forward-fast',
use_cache=False)
document_embeddings: DocumentLSTMEmbeddings = DocumentLSTMEmbeddings(
[embeddings], 128, 1, False)
model = TextClassifier(document_embeddings, label_dict, False)
trainer = ModelTrainer(model, corpus)
trainer.train(results_base_path,
max_epochs=2,
test_mode=True,
checkpoint=True)
trainer = ModelTrainer.load_from_checkpoint(
results_base_path / 'checkpoint.pt', 'TextClassifier', corpus)
trainer.train(results_base_path,
max_epochs=2,
test_mode=True,
checkpoint=True)
# clean up results directory
shutil.rmtree(results_base_path)
def test_train_resume_sequence_tagging_training(results_base_path, tasks_base_path):
corpus = NLPTaskDataFetcher.load_corpora(
[NLPTask.FASHION, NLPTask.GERMEVAL], base_path=tasks_base_path
)
tag_dictionary = corpus.make_tag_dictionary("ner")
embeddings = WordEmbeddings("turian")
model: SequenceTagger = SequenceTagger(
hidden_size=64,
embeddings=embeddings,
tag_dictionary=tag_dictionary,
tag_type="ner",
use_crf=False,
)
trainer = ModelTrainer(model, corpus)
trainer.train(results_base_path, max_epochs=2, test_mode=True, checkpoint=True)
trainer = ModelTrainer.load_from_checkpoint(
results_base_path / "checkpoint.pt", "SequenceTagger", corpus
)
trainer.train(results_base_path, max_epochs=2, test_mode=True, checkpoint=True)
# clean up results directory
shutil.rmtree(results_base_path)
def test_train_resume_sequence_tagging_training(results_base_path,
tasks_base_path):
corpus_1 = flair.datasets.ColumnCorpus(data_folder=(tasks_base_path /
'fashion'),
column_format={
0: 'text',
2: 'ner',
})
corpus_2 = flair.datasets.GERMEVAL(base_path=tasks_base_path)
corpus = MultiCorpus([corpus_1, corpus_2])
tag_dictionary = corpus.make_tag_dictionary('ner')
embeddings = WordEmbeddings('turian')
model = SequenceTagger(hidden_size=64,
embeddings=embeddings,
tag_dictionary=tag_dictionary,
tag_type='ner',
use_crf=False)
trainer = ModelTrainer(model, corpus)
trainer.train(results_base_path,
max_epochs=2,
shuffle=False,
checkpoint=True)
checkpoint = SequenceTagger.load_checkpoint(
(results_base_path / 'checkpoint.pt'))
trainer = ModelTrainer.load_from_checkpoint(checkpoint, corpus)
trainer.train(results_base_path,
max_epochs=2,
shuffle=False,
checkpoint=True)
shutil.rmtree(results_base_path)
def train(params, tagger, corpus):
if tagger is not None:
trainer = create_trainer(tagger, corpus)
else:
print("Resuming training")
trainer = ModelTrainer.load_from_checkpoint(
Path(os.path.join(params["model_output_dirpath"],
"checkpoint.pt")), 'SequenceTagger', corpus)
# trainer.train('./models/tr_glove2_word2vec_embedding_150_epochs_0.15_lr', learning_rate=0.15, mini_batch_size=16, max_epochs=150, checkpoint=True)
trainer.train(params["model_output_dirpath"],
learning_rate=params["learning_rate"],
mini_batch_size=params["mini_batch_size"],
max_epochs=params["max_epochs"],
patience=3,
anneal_factor=0.5,
anneal_against_train_loss=True,
anneal_with_restarts=True,
checkpoint=True,
embeddings_in_memory=True)
def test_train_resume_text_classification_training(results_base_path,
tasks_base_path):
corpus = flair.datasets.ClassificationCorpus((tasks_base_path / 'imdb'))
label_dict = corpus.make_label_dictionary()
embeddings = FlairEmbeddings('news-forward-fast')
document_embeddings = DocumentRNNEmbeddings([embeddings], 128, 1, False)
model = TextClassifier(document_embeddings, label_dict, False)
trainer = ModelTrainer(model, corpus)
trainer.train(results_base_path,
max_epochs=2,
shuffle=False,
checkpoint=True)
checkpoint = TextClassifier.load_checkpoint(
(results_base_path / 'checkpoint.pt'))
trainer = ModelTrainer.load_from_checkpoint(checkpoint, corpus)
trainer.train(results_base_path,
max_epochs=2,
shuffle=False,
checkpoint=True)
shutil.rmtree(results_base_path)
def test_train_resume_sequence_tagging_training(results_base_path,
tasks_base_path):
corpus = NLPTaskDataFetcher.load_corpora(
[NLPTask.FASHION, NLPTask.GERMEVAL], base_path=tasks_base_path)
tag_dictionary = corpus.make_tag_dictionary(u'ner')
embeddings = WordEmbeddings(u'glove')
model = SequenceTagger(hidden_size=64,
embeddings=embeddings,
tag_dictionary=tag_dictionary,
tag_type=u'ner',
use_crf=False)
trainer = ModelTrainer(model, corpus)
trainer.train(results_base_path,
max_epochs=2,
test_mode=True,
checkpoint=True)
trainer = ModelTrainer.load_from_checkpoint(
(results_base_path / u'checkpoint.pt'), u'SequenceTagger', corpus)
trainer.train(results_base_path,
max_epochs=2,
test_mode=True,
checkpoint=True)
shutil.rmtree(results_base_path)
test_file='test.txt',
dev_file='dev.txt',
**options['corpus'])
print(corpus)
# what tag to predict
tag_type = 'ner'
# make the tag dictionary from the corpus
tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type)
# embeddings
if len(args.embeddings_list) == 1:
embeddings = FlairEmbeddings(args.embeddings_list[0])
else:
embeddings = StackedEmbeddings(
[FlairEmbeddings(lm) for lm in args.embeddings_list])
# initialize tagger
tagger = SequenceTagger(embeddings=embeddings,
tag_dictionary=tag_dictionary,
tag_type=tag_type,
**options['sequences_tagger'])
# initialize trainer
if args.continue_training:
checkpoint = tagger.load_checkpoint(args.train_path + 'checkpoint.pt')
trainer = ModelTrainer.load_from_checkpoint(checkpoint, corpus)
else:
trainer = ModelTrainer(tagger,
corpus,
use_tensorboard=args.tensorboard)
# training
trainer.train(args.train_path, **options['training'])
def trainer(file_path: Path, filenames: Tuple[str, str, str], checkpoint: str,
stack: str, n_epochs: int) -> None:
"""Train sentiment model using Flair NLP library:
https://github.com/zalandoresearch/flair/blob/master/resources/docs/TUTORIAL_7_TRAINING_A_MODEL.md
To help provide added context, we can stack Glove, Bert or ELMo embeddings along with Flair embeddings.
"""
# pip install flair allennlp
from flair.datasets import ClassificationCorpus
from flair.embeddings import FlairEmbeddings, DocumentRNNEmbeddings
from flair.models import TextClassifier
from flair.trainers import ModelTrainer
from flair.training_utils import EvaluationMetric
from flair.visual.training_curves import Plotter
if stack == "glove":
from flair.embeddings import WordEmbeddings
stacked_embedding = WordEmbeddings('glove')
elif stack == "elmo":
from flair.embeddings import ELMoEmbeddings
stacked_embedding = ELMoEmbeddings('original')
elif stack == "bert":
from flair.embeddings import BertEmbeddings
stacked_embedding = BertEmbeddings('bert-base-cased')
else:
stacked_embedding = None
# Define and Load corpus from the provided dataset
train, dev, test = filenames
corpus = ClassificationCorpus(
file_path,
train_file=train,
dev_file=dev,
test_file=test,
)
# Create label dictionary from provided labels in data
label_dict = corpus.make_label_dictionary()
# Stack Flair string-embeddings with optional embeddings
word_embeddings = list(
filter(None, [
stacked_embedding,
FlairEmbeddings('news-forward'),
FlairEmbeddings('news-backward'),
]))
# Initialize document embedding by passing list of word embeddings
document_embeddings = DocumentRNNEmbeddings(
word_embeddings,
hidden_size=512,
reproject_words=True,
reproject_words_dimension=256,
)
# Define classifier
classifier = TextClassifier(document_embeddings,
label_dictionary=label_dict,
multi_label=False)
if not checkpoint:
trainer = ModelTrainer(classifier, corpus)
else:
# If checkpoint file is defined, resume training
checkpoint = classifier.load_checkpoint(Path(checkpoint))
trainer = ModelTrainer.load_from_checkpoint(checkpoint, corpus)
# Begin training (enable checkpointing to continue training at a later time, if desired)
trainer.train(
base_path=file_path,
#EvaluationMetric.MACRO_F1_SCORE,
max_epochs=n_epochs,
checkpoint=True)
# Plot curves and store weights and losses
plotter = Plotter()
plotter.plot_training_curves(file_path + '/loss.tsv')
plotter.plot_weights(file_path + '/weights.txt')
from pathlib import Path
from flair.trainers import ModelTrainer
from flair.models import SequenceTagger
from flair.data import TaggedCorpus
from flair.data_fetcher import NLPTaskDataFetcher, NLPTask
from flair.embeddings import TokenEmbeddings, WordEmbeddings, StackedEmbeddings
from typing import List
import flair, torch
flair.device = torch.device('cpu')
columns = {0: 'text', 1: 'ner'}
data_folder = '../'
corpus: TaggedCorpus = NLPTaskDataFetcher.load_column_corpus(
data_folder,
columns,
train_file="de-da-te-ta.10E-4percent.conll.84max.train.txt",
test_file="de-da-te-ta.10E-4percent.conll.84max.test.txt",
dev_file="de-da-te-ta.10E-4percent.conll.84max.dev.txt")
trainer = ModelTrainer.load_from_checkpoint(
Path('./models/example-ner-tr-embedding/checkpoint.pt'), 'SequenceTagger',
corpus)
trainer.train('./models/example-ner-tr-embedding-continued',
learning_rate=0.15,
mini_batch_size=32,
max_epochs=150,
checkpoint=True)