def make_sets():
training_data = []
training_labels = []
prediction_data = []
prediction_labels = []
for emotion in emotions:
training, prediction = get_files(emotion)
for item in training:
training_data.append(load_image(item))
training_labels.append(emotions.index(emotion))
for item in prediction:
prediction_data.append(load_image(item))
prediction_labels.append(emotions.index(emotion))
return training_data, training_labels, prediction_data, prediction_labels
def make_sets():
"""
method used to create datasets for all emotions. It loads both images and its labels to memory into training and test labels
"""
training_data = []
training_labels = []
prediction_data = []
prediction_labels = []
for emotion in emotions:
training, prediction = get_files(emotion)
for item in training:
training_data.append(load_image(item))
training_labels.append(emotions.index(emotion))
for item in prediction:
prediction_data.append(load_image(item))
prediction_labels.append(emotions.index(emotion))
return training_data, training_labels, prediction_data, prediction_labels
def make_sets():
"""
method used to create datasets for all emotions. It loads both images and its labels to memory into training and test labels
"""
training_data = []
training_labels = []
prediction_data = []
prediction_labels = []
for emotion in emotions:
training, prediction = get_files(emotion)
for item in training:
training_data.append(load_image(item))
training_labels.append(emotions.index(emotion))
for item in prediction:
prediction_data.append(load_image(item))
prediction_labels.append(emotions.index(emotion))
return training_data, training_labels, prediction_data, prediction_labels
