def train_model(model):
for epoch in range(epochs):
print("Epoch %d/%d" % (epoch, epochs))
a = Progbar(len(train_batch_len))
for i, batch in enumerate(
iterate_minibatches(train_batch, train_batch_len)):
labels, tokens, casing, char = batch
model.train_on_batch([tokens, casing, char], labels)
a.update(i)
print(' ')
return model
def train(self):
"""Default training"""
self.f1_test_history = []
self.f1_dev_history = []
for epoch in range(self.epochs):
print("Epoch {}/{}".format(epoch, self.epochs))
for i, batch in enumerate(
iterate_minibatches(self.train_batch,
self.train_batch_len)):
labels, tokens, casing, char = batch
self.model.train_on_batch([tokens, casing, char], labels)
# compute F1 scores
predLabels, correctLabels = self.tag_dataset(
self.test_batch, self.model)
pre_test, rec_test, f1_test = compute_f1(predLabels, correctLabels,
self.idx2Label)
self.f1_test_history.append(f1_test)
print("f1 test ", round(f1_test, 4))
predLabels, correctLabels = self.tag_dataset(
self.dev_batch, self.model)
pre_dev, rec_dev, f1_dev = compute_f1(predLabels, correctLabels,
self.idx2Label)
self.f1_dev_history.append(f1_dev)
print("f1 dev ", round(f1_dev, 4), "\n")
print("Final F1 test score: ", f1_test)
print("Training finished.")
# save model
self.modelName = "{}_{}_{}_{}_{}_{}_{}".format(
self.epochs, self.dropout, self.dropout_recurrent,
self.lstm_state_size, self.conv_size, self.learning_rate,
self.optimizer.__class__.__name__)
modelName = self.modelName + ".h5"
self.model.save(modelName)
print("Model weights saved.")
self.model.set_weights(self.init_weights) # clear model
print("Model weights cleared.")
def train(model, train_set, epochs, package):
train_batch, train_batch_len = createBatches(train_set)
for epoch in range(epochs):
print("Epoch %d/%d" % (epoch, epochs))
a = Progbar(len(train_batch_len))
for i, batch in enumerate(
iterate_minibatches(train_batch, train_batch_len)):
labels, tokens, casing, char = batch
if package.modelName == "LSTM_word":
with tf.device('/gpu:0'):
model.fit([tokens], labels, verbose=0)
elif package.modelName == "LSTM_word_char":
with tf.device('/gpu:0'):
model.fit([tokens, casing, char], labels, verbose=0)
a.update(i)
print(' ')
return model
char = Dropout(0.5)(char)
output = concatenate([words, casing, char])
output = Bidirectional(
LSTM(200, return_sequences=True, dropout=0.50,
recurrent_dropout=0.25))(output)
output = TimeDistributed(Dense(len(label2Idx), activation='softmax'))(output)
model = Model(inputs=[words_input, casing_input, character_input],
outputs=[output])
model.compile(loss='sparse_categorical_crossentropy', optimizer='nadam')
model.summary()
# plot_model(model, to_file='model.png')
for epoch in range(epochs):
print("Epoch %d/%d" % (epoch, epochs))
a = Progbar(len(train_batch_len))
for i, batch in enumerate(iterate_minibatches(train_batch,
train_batch_len)):
labels, tokens, casing, char = batch
model.train_on_batch([tokens, casing, char], labels)
a.update(i)
a.update(i + 1)
print(' ')
model.save("models/model.h5")
# Performance on dev dataset
predLabels, correctLabels = tag_dataset(dev_batch)
pre_dev, rec_dev, f1_dev = compute_f1(predLabels, correctLabels, idx2Label)
print("Dev-Data: Prec: %.3f, Rec: %.3f, F1: %.3f" % (pre_dev, rec_dev, f1_dev))
# Performance on test dataset
predLabels, correctLabels = tag_dataset(test_batch)
output = concatenate([words, casing, char])
output = Bidirectional(
LSTM(200, return_sequences=True, dropout=0.50,
recurrent_dropout=0.25))(output)
output = TimeDistributed(Dense(len(label2Idx),
activation='softmax'))(output)
model = Model(inputs=[words_input, casing_input, character_input],
outputs=[output])
model.compile(loss='sparse_categorical_crossentropy', optimizer='nadam')
model.summary()
# plot_model(model, to_file='model.png')
for epoch in range(epochs):
print("Epoch %d/%d" % (epoch, epochs))
for i, batch in enumerate(
iterate_minibatches(train_batch, train_batch_len)):
labels, tokens, casing, char = batch
model.train_on_batch([tokens, casing, char], labels)
print(' ')
# Performance on dev dataset
predLabels, correctLabels = tag_dataset(dev_batch)
pre_dev, rec_dev, f1_dev = compute_f1(predLabels, correctLabels, idx2Label)
print("Dev-Data: Prec: %.3f, Rec: %.3f, F1: %.3f" %
(pre_dev, rec_dev, f1_dev))
# Performance on test dataset
predLabels, correctLabels = tag_dataset(test_batch)
pre_test, rec_test, f1_test = compute_f1(predLabels, correctLabels,
idx2Label)
print("Test-Data: Prec: %.3f, Rec: %.3f, F1: %.3f" %
