instances = np.apply_along_axis(utils.add_instances,
category_column=CATEGORY_COLUMN,
instance_column=INSTANCE_COLUMN,
axis=1,
arr=selected_data)
selected_data[:, CATEGORY_COLUMN] = instances
# Bring class labels to the range within the number of the classes.
fitted_class_labels = utils.fit_class_labels(
selected_data[:, CATEGORY_COLUMN], args.num_classes)
selected_data[:, CATEGORY_COLUMN] = fitted_class_labels
train_data = selected_data[np.in1d(selected_data[:, SESSION_COLUMN],
TRAIN_SESSIONS)]
train_data = utils.reduce_number_of_frames(train_data, FACTOR_FRAMES)
train_data = utils.select_frames_per_session(
train_data, NUMBER_FRAMES, FACTOR_FRAMES, CATEGORY_COLUMN,
SESSION_COLUMN, IMAGE_NAME_COLUMN, TRAIN_SESSIONS)
test_data = selected_data[np.in1d(selected_data[:, SESSION_COLUMN],
TEST_SESSIONS)]
# ------------------------------------ Batch learning---------------------------------------------------------------
if BATCH_LEARNING:
learning.batch_learning(train_data, test_data, args)
# ------------------------------------ Iterative learning ----------------------------------------------------------
if ITERATIVE_LEARNING:
learning.iterative_learning(train_data, test_data, args,
CATEGORY_COLUMN)
# frames is 8. In this case it will be reduced to 4 and 2, respectively.
# ------------------------------------ Initialization --------------------------------------------------------------
rgwr = GammaGWR()
utils = Utilities()
learning = Learning()
args = utils.parse_arguments()
# Get data.
original_data = utils.load_data(args.dataset).values
original_data_normalized = utils.normalize_data(original_data,
DATA_DIMENSION)
train_data = original_data_normalized[np.in1d(
original_data_normalized[:, SESSION_COLUMN], TRAIN_SESSIONS)]
train_data = utils.reduce_number_of_frames(train_data, FACTOR_FRAMES)
test_data = original_data_normalized[np.in1d(
original_data_normalized[:, SESSION_COLUMN], TEST_SESSIONS)]
# ------------------------------------ Batch learning---------------------------------------------------------------
if BATCH_LEARNING:
learning.batch_learning(train_data, test_data, args)
# ------------------------------------ Iterative learning ----------------------------------------------------------
if ITERATIVE_LEARNING:
learning.iterative_learning(train_data, test_data, args,
INSTANCE_COLUMN)