import numpy as np
from utils.preprocessing import *
from functools import partial
from utils.research_preprocessing import add_occlusions
dataset.apply(clean_repeat_points)
NUM_SAMPLES = 50
ANGLES_TO_ROTATE = [5, 10, 15, 45, -5, -10, -15, -45]
DROPOUTS_TO_TRY = np.linspace(0.0, 0.99, 20)
scores = []
for drop in DROPOUTS_TO_TRY:
curr = dataset.copy()
curr.apply(partial(add_occlusions, dropout_percentage=drop))
curr.apply(apply_mean_centering)
curr.apply(apply_unit_distance_normalization)
curr.apply(
partial(spline_interpolate_and_resample, num_samples=NUM_SAMPLES))
curr.expand_many(partial(rotate_digit, degrees=ANGLES_TO_ROTATE))
curr.expand(reverse_digit_sequence)
X_train = np.array(curr.train_data)
# Convert labels to numpy array and OneHot encode them
encoder, Y_train, _, _ = curr.onehot_encode_labels()
# evaluate
score = model.evaluate(X_train, Y_train)[1]
print("occlusion percentage: %.2f%%, acc: %.3f%%" %
(drop * 100.0, score * 100.0))
scores.append(score)
