def three_point_five_second_bullet():
filepath = r"data/pict.dat"
pictures_matrix = ld.get_pictures(filepath)
# Learning
number_of_random_samples = 15
max_training_num = np.arange(3, 4 + number_of_random_samples,
1) # [3,4, 5, 6, 7]
np.random.seed(42)
max_iter = 1
percentage_check = np.arange(15, 20, 5)
training = np.zeros((3 + number_of_random_samples,
pictures_matrix.shape[1] * pictures_matrix.shape[2]))
for i in range(3):
training[i] = np.ravel(pictures_matrix[i])
for i in range(number_of_random_samples):
training[i + 3] = get_random_image()
accuracy_mean = accuracy_with_sample_images(percentage_check,
max_training_num, max_iter,
training)
plt.plot(max_training_num, accuracy_mean[0, :, 0], label='p1')
plt.plot(max_training_num, accuracy_mean[0, :, 1], label='p2')
plt.plot(max_training_num, accuracy_mean[0, :, 2], label='p3')
plt.title("Accuracy as a function of Number of Pictures Memorized")
plt.legend()
plt.xlabel("Number of Patterns memorized-trained on")
plt.ylabel("Accuracy (% pixels)")
plt.show()
def three_point_five_first_bullet():
# Load data
filepath = r"data/pict.dat"
pictures_matrix = ld.get_pictures(filepath)
# Learning
max_training_num = [3, 4, 5, 6, 7]
training = np.zeros((max_training_num[-1],
pictures_matrix.shape[1] * pictures_matrix.shape[2]))
for i in range(max_training_num[-1]):
training[i] = np.ravel(pictures_matrix[i])
np.random.seed(42)
max_iter = 5
percentage_check = np.arange(15, 20, 5)
accuracy_mean = accuracy_with_sample_images(percentage_check,
max_training_num, max_iter,
training)
plt.plot(max_training_num, accuracy_mean[0, :, 0], label='p1')
plt.plot(max_training_num, accuracy_mean[0, :, 1], label='p2')
plt.plot(max_training_num, accuracy_mean[0, :, 2], label='p3')
plt.title("Accuracy as a function of Number of Pictures Memorized")
plt.legend()
plt.xlabel("Number of Patterns memorized-trained on")
plt.ylabel("Accuracy (% pixels)")
plt.show()
import load_data as ld
import functions as fun
import numpy as np
import matplotlib.pyplot as plt
filepath = r"data/pict.dat"
pictures_matrix = ld.get_pictures(filepath)
# for i in range(pictures_matrix.shape[0]):
# plt.imshow(pictures_matrix[i])
# plt.show()
number_training = 3
number_of_distorted = 2
training = np.zeros(
(number_training, pictures_matrix.shape[1] * pictures_matrix.shape[2]))
for i in range(number_training):
training[i] = np.ravel(pictures_matrix[i])
weights = fun.fit(training)
#Taking distorted patterns
distorted = np.zeros(
(number_of_distorted, pictures_matrix.shape[1] * pictures_matrix.shape[2]))
distorted[0] = np.ravel(pictures_matrix[9])
distorted[1] = np.ravel(pictures_matrix[10])
#Energy at attractors
print('Energy of Attractors')
for i in range(number_training):
energy = fun.compute_lyapunov_energy(training[i].reshape(1, -1), weights)
print(energy)