reader = ReadData(path_file=args.dataset,
embedding_config=embedding,
data_shape=inputs,
train_val_split=args.train_val_split,
sentence_pair=True)
else:
reader = ReadData(path_file=args.dataset,
embedding_config=embedding,
data_shape=inputs,
train_val_split=args.train_val_split,
sentence_pair=False)
print('Reading Validation Data ..')
val_x, val_y = reader.read_val()
train_generator = reader.generator()
log_dir = args.model
logging = TrainValTensorBoard(log_dir=log_dir)
checkpoint = ModelCheckpoint(os.path.join(
log_dir, 'ep{epoch:03d}-val_loss{val_loss:.3f}-val_acc{val_acc:.3f}.h5'),
monitor='val_loss',
save_weights_only=True,
save_best_only=True,
period=1)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.1,
patience=3,
model = RecurrentCNN(no_filters=hidden_size, no_classes=args.no_classes)
elif args.model == 'bilstm_rcnn':
inputs = [(args.no_comments, 512), (30, 1536)]
model = BiLSTMRecurrentCNN(hidden_size, no_classes=args.no_classes)
model = model.build(inputs)
model.compile(loss='binary_crossentropy', optimizer=Adam(lr=args.learning_rate), metrics=['accuracy'])
model.summary()
if args.check_build:
exit()
reader = ReadData(dataset=args.dataset, text_embedding_path=args.text_embedding,
video_feature_path=args.video_features, data_shape=inputs, train_val_split=args.train_val_split)
train_generator = reader.generator(batch_size=args.batch_size)
val_generator = reader.generator_val(batch_size=args.batch_size)
log_dir = args.logs + '_' + args.model
logging = TrainValTensorBoard(log_dir=log_dir)
checkpoint = ModelCheckpoint(os.path.join(log_dir, 'ep{epoch:03d}-val_loss{val_loss:.3f}-val_acc{val_acc:.3f}.h5'),
monitor='val_acc', save_weights_only=True, save_best_only=True, period=1)
reduce_lr = ReduceLROnPlateau(monitor='val_acc', factor=0.1, patience=3, verbose=1)
early_stopping = EarlyStopping(monitor='val_acc', min_delta=0, patience=5, verbose=1)
print('Training on {} samples and Validating on {} samples.'.format(reader.train_size, reader.val_size))
model.fit_generator(generator=train_generator, steps_per_epoch=int(reader.train_size/args.batch_size),
validation_data=val_generator, epochs=args.epochs, validation_steps=int(reader.val_size/args.batch_size),
callbacks=[logging, checkpoint, reduce_lr, early_stopping])
