def train_cnn_model(emb_layer, x_train, y_train, x_val, y_val, opt):
model = CNN(embedding_layer=emb_layer,
num_words=opt.n_words,
embedding_dim=opt.embed_dim,
filter_sizes=opt.cnn_filter_shapes,
feature_maps=opt.filter_sizes,
max_seq_length=opt.sent_len,
dropout_rate=opt.dropout_ratio,
hidden_units=200,
nb_classes=2).build_model()
model.compile(loss='categorical_crossentropy',
optimizer=optimizers.Adam(),
metrics=['accuracy'])
# y_train = y_train.reshape(-1, 1)
# model = build_model(emb_layer, opt)
print(model.summary())
early_stopping = EarlyStopping(monitor='val_loss', patience=2)
history = model.fit(x_train,
y_train,
epochs=opt.cnn_epoch,
batch_size=opt.batch_size,
verbose=1,
validation_data=(x_val, y_val),
callbacks=[early_stopping])
with open("CNN_train_history.txt", "w") as f:
print(history.history, file=f)
return model
def train_baseline_cnn(emb_layer, x_train, y_train, x_val, y_val, opt):
model = CNN(embedding_layer=emb_layer,
num_words=opt.transfer_n_words,
embedding_dim=opt.baseline_embed_dim,
filter_sizes=opt.cnn_filter_shapes,
feature_maps=opt.filter_sizes,
max_seq_length=opt.baseline_sent_len,
dropout_rate=opt.baseline_drop_out_ratio,
hidden_units=200,
nb_classes=2).build_model()
model.compile(loss='categorical_crossentropy',
optimizer=optimizers.Adam(),
metrics=['accuracy'])
# y_train = y_train.reshape(-1, 1)
# model = build_model(emb_layer, opt)
print(model.summary())
tb_call_back = TensorBoard(log_dir=f'{opt.tbpath}/baseline_cnn_{time()}',
histogram_freq=1,
write_graph=True,
write_images=True)
checkpoint = ModelCheckpoint("baseline_cnn.h5",
monitor='val_acc',
verbose=1,
save_best_only=True,
save_weights_only=False,
mode='auto',
period=1)
early_stopping = EarlyStopping(monitor='val_loss', patience=2)
history = model.fit(x_train,
y_train,
epochs=opt.baseline_epochs,
batch_size=opt.baseline_batchsize,
verbose=1,
validation_data=(x_val, y_val),
callbacks=[early_stopping, tb_call_back, checkpoint])
with open("CNN_train_baseline_history.txt", "w") as f:
print(history.history, file=f)
return model