def predict(main_config, model_config, model, experiment_name):
model = MODELS[model]
model_dir = str(main_config['DATA']['model_dir'])
vectorizer = DatasetVectorizer(model_dir)
max_doc_len = vectorizer.max_sentence_len
vocabulary_size = vectorizer.vocabulary_size
model = model(max_doc_len, vocabulary_size, main_config, model_config)
with tf.Session() as session:
saver = tf.train.Saver()
last_checkpoint = tf.train.latest_checkpoint('{}/{}'.format(
model_dir, experiment_name))
saver.restore(session, last_checkpoint)
while True:
x1 = input('First sentence:')
x2 = input('Second sentence:')
x1_sen = vectorizer.vectorize(x1)
x2_sen = vectorizer.vectorize(x2)
feed_dict = {
model.x1: x1_sen,
model.x2: x2_sen,
model.is_training: False
}
prediction = session.run([model.temp_sim], feed_dict=feed_dict)
print(prediction)
def predict(main_config, model_config, model):
model_name = '{}_{}'.format(model, main_config['PARAMS']['embedding_size'])
model = MODELS[model_name]
model_dir = str(main_config['DATA']['model_dir'])
vectorizer = DatasetVectorizer(model_dir)
max_doc_len = vectorizer.max_sentence_len
vocabulary_size = vectorizer.vocabulary_size
model = model(max_doc_len, vocabulary_size, main_config, model_config)
with tf.Session() as session:
saver = tf.train.Saver()
last_checkpoint = tf.train.latest_checkpoint('{}/{}/model'.format(
model_dir, model_name))
saver.restore(session, last_checkpoint)
while True:
x = input('Text:')
x_sen = vectorizer.vectorize(x)
feed_dict = {model.x: x_sen}
prediction = session.run([model.temp_sim], feed_dict=feed_dict)
print(prediction)
class MultiheadSiameseNetGuiDemo:
def __init__(self, master):
self.frame = master
self.frame.title('Multihead Siamese Nets')
sample1 = StringVar(master, value=SAMPLE_SENTENCE1)
sample2 = StringVar(master, value=SAMPLE_SENTENCE2)
self.first_sentence_entry = Entry(
self.frame,
width=50,
font="Helvetica {}".format(GUI_FONT_SIZE),
textvariable=sample1)
self.second_sentence_entry = Entry(
self.frame,
width=50,
font="Helvetica {}".format(GUI_FONT_SIZE),
textvariable=sample2)
self.predictButton = Button(self.frame,
text='Predict',
font="Helvetica {}".format(GUI_FONT_SIZE),
command=self.predict)
self.clearButton = Button(self.frame,
text='Clear',
command=self.clear,
font="Helvetica {}".format(GUI_FONT_SIZE))
self.resultLabel = Label(self.frame,
text='Result',
font="Helvetica {}".format(GUI_FONT_SIZE))
self.first_sentence_label = Label(
self.frame,
text='Sentence 1',
font="Helvetica {}".format(GUI_FONT_SIZE))
self.second_sentence_label = Label(
self.frame,
text='Sentence 2',
font="Helvetica {}".format(GUI_FONT_SIZE))
self.main_config = init_config()
self.model_dir = str(self.main_config['DATA']['model_dir'])
model_dirs = [os.path.basename(x[0]) for x in os.walk(self.model_dir)]
self.visualize_attentions = IntVar()
self.visualize_attentions_checkbox = Checkbutton(
master,
text="Visualize attention weights",
font="Helvetica {}".format(int(GUI_FONT_SIZE / 2)),
variable=self.visualize_attentions,
onvalue=1,
offvalue=0)
variable = StringVar(master)
variable.set('Choose a model...')
self.model_type = OptionMenu(master,
variable,
*model_dirs,
command=self.load_model)
self.model_type.configure(font=('Helvetica', GUI_FONT_SIZE))
self.first_sentence_entry.grid(row=0, column=1, columnspan=4)
self.first_sentence_label.grid(row=0, column=0, sticky=E)
self.second_sentence_entry.grid(row=1, column=1, columnspan=4)
self.second_sentence_label.grid(row=1, column=0, sticky=E)
self.model_type.grid(row=2, column=1, sticky=W + E, ipady=1)
self.predictButton.grid(row=2, column=2, sticky=W + E, ipady=1)
self.clearButton.grid(row=2, column=3, sticky=W + E, ipady=1)
self.resultLabel.grid(row=2, column=4, sticky=W + E, ipady=1)
self.vectorizer = DatasetVectorizer(self.model_dir)
self.max_doc_len = self.vectorizer.max_sentence_len
self.vocabulary_size = self.vectorizer.vocabulary_size
self.session = tf.Session()
self.model = None
def predict(self):
if self.model:
sentence1 = self.first_sentence_entry.get()
sentence2 = self.second_sentence_entry.get()
x1_sen = self.vectorizer.vectorize(sentence1)
x2_sen = self.vectorizer.vectorize(sentence2)
feed_dict = {
self.model.x1: x1_sen,
self.model.x2: x2_sen,
self.model.is_training: False
}
if self.visualize_attentions.get():
prediction, at1, at2 = np.squeeze(
self.session.run([
self.model.predictions,
self.model.debug_vars['attentions_x1'],
self.model.debug_vars['attentions_x2']
],
feed_dict=feed_dict))
visualization.visualize_attention_weights(at1, sentence1)
visualization.visualize_attention_weights(at2, sentence2)
else:
prediction = np.squeeze(
self.session.run(self.model.predictions,
feed_dict=feed_dict))
prediction = np.round(prediction, 2)
self.resultLabel['text'] = prediction
if prediction < 0.5:
self.resultLabel.configure(foreground="red")
else:
self.resultLabel.configure(foreground="green")
else:
messagebox.showerror("Error",
"Choose a model to make a prediction.")
def clear(self):
self.first_sentence_entry.delete(0, 'end')
self.second_sentence_entry.delete(0, 'end')
self.resultLabel['text'] = ''
def load_model(self, model_name):
if 'multihead' in model_name:
self.visualize_attentions_checkbox.grid(row=2,
column=0,
sticky=W + E,
ipady=1)
else:
self.visualize_attentions_checkbox.grid_forget()
tf.reset_default_graph()
self.session = tf.Session()
logger.info('Loading model: %s', model_name)
model = MODELS[model_name.split('_')[0]]
model_config = init_config(model_name.split('_')[0])
self.model = model(self.max_doc_len, self.vocabulary_size,
self.main_config, model_config)
saver = tf.train.Saver()
last_checkpoint = tf.train.latest_checkpoint('{}/{}'.format(
self.model_dir, model_name))
saver.restore(self.session, last_checkpoint)
logger.info('Loaded model from: %s', last_checkpoint)