def load_from_checkpoint(checkpoint_file: Path,
model_type: str,
corpus: Corpus,
optimizer: Optimizer = SGD):
if model_type == 'SequenceTagger':
checkpoint = SequenceTagger.load_checkpoint(checkpoint_file)
return ModelTrainer(
checkpoint['model'],
corpus,
optimizer,
epoch=checkpoint['epoch'],
loss=checkpoint['loss'],
optimizer_state=checkpoint['optimizer_state_dict'],
scheduler_state=checkpoint['scheduler_state_dict'])
if model_type == 'TextClassifier':
checkpoint = TextClassifier.load_checkpoint(checkpoint_file)
return ModelTrainer(
checkpoint['model'],
corpus,
optimizer,
epoch=checkpoint['epoch'],
loss=checkpoint['loss'],
optimizer_state=checkpoint['optimizer_state_dict'],
scheduler_state=checkpoint['scheduler_state_dict'])
raise ValueError(
'Incorrect model type! Use one of the following: "SequenceTagger", "TextClassifier".'
)
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 load_from_checkpoint(
checkpoint_file: Path,
model_type: str,
corpus: Corpus,
optimizer: Optimizer = SGD,
):
if model_type == "SequenceTagger":
checkpoint = SequenceTagger.load_checkpoint(checkpoint_file)
return ModelTrainer(
checkpoint["model"],
corpus,
optimizer,
epoch=checkpoint["epoch"],
loss=checkpoint["loss"],
optimizer_state=checkpoint["optimizer_state_dict"],
scheduler_state=checkpoint["scheduler_state_dict"],
)
if model_type == "TextClassifier":
checkpoint = TextClassifier.load_checkpoint(checkpoint_file)
return ModelTrainer(
checkpoint["model"],
corpus,
optimizer,
epoch=checkpoint["epoch"],
loss=checkpoint["loss"],
optimizer_state=checkpoint["optimizer_state_dict"],
scheduler_state=checkpoint["scheduler_state_dict"],
)
raise ValueError(
'Incorrect model type! Use one of the following: "SequenceTagger", "TextClassifier".'
)
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)
from __future__ import absolute_import
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
