def test_train(self):
model_config = ModelConfig()
training_config = TrainingConfig()
train_path = os.path.join(DATA_ROOT, 'train.txt')
valid_path = os.path.join(DATA_ROOT, 'valid.txt')
x_train, y_train = load_data_and_labels(train_path)
x_valid, y_valid = load_data_and_labels(valid_path)
p = prepare_preprocessor(x_train, y_train)
p.save(os.path.join(SAVE_ROOT, 'preprocessor.pkl'))
embeddings = load_word_embeddings(p.vocab_word, EMBEDDING_PATH,
model_config.word_embedding_size)
model_config.char_vocab_size = len(p.vocab_char)
model = SeqLabeling(model_config, embeddings, len(p.vocab_tag))
trainer = anago.Trainer(model,
training_config,
checkpoint_path=LOG_ROOT,
save_path=SAVE_ROOT,
preprocessor=p,
embeddings=embeddings)
trainer.train(x_train, y_train, x_valid, y_valid)
model.save(os.path.join(SAVE_ROOT, 'model_weights.h5'))
def train(self, x_train, y_train, x_valid=None, y_valid=None):
# Prepare training and validation data(steps, generator)
train_steps, train_batches = batch_iter(
list(zip(x_train, y_train)),
self.training_config.batch_size,
preprocessor=self.preprocessor)
valid_steps, valid_batches = batch_iter(
list(zip(x_valid, y_valid)),
self.training_config.batch_size,
preprocessor=self.preprocessor)
# Build the model
model = SeqLabeling(self.model_config, self.embeddings,
len(self.preprocessor.vocab_tag))
model.compile(
loss=model.crf.loss,
optimizer=Adam(lr=self.training_config.learning_rate),
)
# Prepare callbacks for training
callbacks = get_callbacks(
log_dir=self.checkpoint_path,
tensorboard=self.tensorboard,
eary_stopping=self.training_config.early_stopping,
valid=(valid_steps, valid_batches, self.preprocessor))
# Train the model
model.fit_generator(generator=train_batches,
steps_per_epoch=train_steps,
epochs=self.training_config.max_epoch,
callbacks=callbacks)
# Save the model
model.save(os.path.join(self.save_path, 'model_weights.h5'))
DATA_ROOT = 'data/conll2003/en/ner'
SAVE_ROOT = './models' # trained model
LOG_ROOT = './logs' # checkpoint, tensorboard
embedding_path = '/media/jan/OS/Dataset/WordEmbeddings/wiki.en.vec'
model_config = ModelConfig()
training_config = TrainingConfig()
model_path = os.path.join(SAVE_ROOT, 'mymodel.h5')
train_path = os.path.join(DATA_ROOT, 'train.small.txt')
valid_path = os.path.join(DATA_ROOT, 'valid.small.txt')
x_train, y_train = load_data_and_labels(train_path)
x_valid, y_valid = load_data_and_labels(valid_path)
p = prepare_preprocessor(x_train, y_train)
embeddings = load_word_embeddings(p.vocab_word, embedding_path,
model_config.word_embedding_size)
model_config.vocab_size = len(p.vocab_word)
model_config.char_vocab_size = len(p.vocab_char)
model = SeqLabeling(model_config, embeddings, len(p.vocab_tag))
trainer = anago.Trainer(model,
training_config,
checkpoint_path=LOG_ROOT,
save_path=SAVE_ROOT,
preprocessor=p)
trainer.train(x_train, y_train, x_valid, y_valid)
evaluator = anago.Evaluator(model, preprocessor=p)
model.save(model_path)
class Sequence(object):
config_file = 'config.json'
weight_file = 'model_weights.h5'
preprocessor_file = 'preprocessor.pkl'
def __init__(self,
char_emb_size=25,
word_emb_size=100,
char_lstm_units=25,
word_lstm_units=100,
dropout=0.5,
char_feature=True,
crf=True,
batch_size=1024,
optimizer='adam',
learning_rate=0.001,
lr_decay=0.9,
clip_gradients=5.0,
max_epoch=15,
early_stopping=True,
patience=3,
train_embeddings=True,
max_checkpoints_to_keep=5,
log_dir=None,
embeddings=()):
self.model_config = ModelConfig(char_emb_size, word_emb_size,
char_lstm_units, word_lstm_units,
dropout, char_feature, crf)
self.training_config = TrainingConfig(batch_size, optimizer,
learning_rate, lr_decay,
clip_gradients, max_epoch,
early_stopping, patience,
train_embeddings,
max_checkpoints_to_keep)
self.model = None
self.p = None
self.log_dir = log_dir
self.embeddings = embeddings
def train(self,
x_train,
y_train,
x_valid=None,
y_valid=None,
vocab_init=None,
verbose=1):
self.p = prepare_preprocessor(x_train, y_train, vocab_init=vocab_init)
embeddings = filter_embeddings(self.embeddings, self.p.vocab_word,
self.model_config.word_embedding_size)
self.model_config.vocab_size = len(self.p.vocab_word)
self.model_config.char_vocab_size = len(self.p.vocab_char)
self.model = SeqLabeling(self.model_config, embeddings,
len(self.p.vocab_tag))
if not os.path.exists(self.log_dir):
print('Successfully made a directory: {}'.format(self.log_dir))
os.mkdir(self.log_dir)
self.p.save(os.path.join(self.log_dir, self.preprocessor_file))
self.model_config.save(os.path.join(self.log_dir, self.config_file))
print('Successfully save config and preprocess files')
trainer = Trainer(self.model,
self.training_config,
checkpoint_path=self.log_dir,
preprocessor=self.p)
return trainer.train(x_train, y_train, x_valid, y_valid, verbose)
def eval(self, x_test, y_test):
if self.model:
evaluator = Evaluator(self.model, preprocessor=self.p)
evaluator.eval(x_test, y_test)
else:
raise (OSError('Could not find a model. Call load(dir_path).'))
def analyze(self, words):
if self.model:
tagger = Tagger(self.model, preprocessor=self.p)
return tagger.analyze(words)
else:
raise (OSError('Could not find a model. Call load(dir_path).'))
def save(self, dir_path):
self.p.save(os.path.join(dir_path, self.preprocessor_file))
self.model_config.save(os.path.join(dir_path, self.config_file))
self.model.save(os.path.join(dir_path, self.weight_file))
@classmethod
def load(cls, dir_path):
self = cls()
self.p = WordPreprocessor.load(
os.path.join(dir_path, cls.preprocessor_file))
config = ModelConfig.load(os.path.join(dir_path, cls.config_file))
dummy_embeddings = np.zeros(
(config.vocab_size, config.word_embedding_size), dtype=np.float32)
self.model = SeqLabeling(config,
dummy_embeddings,
ntags=len(self.p.vocab_tag))
self.model.load(filepath=os.path.join(dir_path, cls.weight_file))
self.model._make_predict_function()
return self