def part7(alpha, EPS, max_iters):
'''
Plot the performance of the classifiers on the training and validation sets vs the size of the training set.
:param alpha: alpha
:param EPS: epsilon
:param max_iters: maximum iterations
:return: void
'''
# Get training data, validation data and testing data from part2
im_data_training, im_data_validation, im_data_testing = part2()
# Get required x_train and prepare labels for training data
x_train, y_train = dataExtraction.prepare_training_data_label_by_actor_order_2(
im_data_training, [0, 1, 2, 3, 4, 5], 70)
# Add constant values for each image data in x_train
x_train = np.concatenate(
(x_train, np.ones([x_train.shape[0], 1])), axis=1) / 255
# Prepare for calculating gradient in two ways
theta0 = np.ones((1025, 6)) * 0.01
# Train classifiers
theta, costs, iters = lr.gradient_descent(
lr.new_quadratic_cost_function,
lr.new_derivative_quadratic_cost_function, x_train, y_train, theta0,
alpha, EPS, max_iters)
# Performance on training set
y_hypothesis = lr.hypothesis(theta, x_train)
accuracy = accuracy_compute.accuracy_2(y_train, y_hypothesis)
print(accuracy)
# Performance on validation set
x_valid, y_valid = dataExtraction.prepare_training_data_label_by_actor_order_2(
im_data_validation, [0, 1, 2, 3, 4, 5], 10)
x_valid = np.concatenate(
(x_valid, np.ones([x_valid.shape[0], 1])), axis=1) / 255
y_hypothesis = lr.hypothesis(theta, x_valid)
accuracy = accuracy_compute.accuracy_2(y_valid, y_hypothesis)
print(accuracy)
return theta
def part4():
'''
Display the θs that you obtain by training using the full training dataset, and by training using a training set that contains only two images of each actor.
:return: void
'''
# Get training data, validation data and testing data from part2
im_data_training, im_data_validation, im_data_testing = part2()
# Using full training set of Baldwin and Carell
# 500 iterations
theta_full, iters_full = part3(1e-5, 1e-6, 5000)
# 5000 iterations
# theta_full, iters_full = part3(1e-5, 1e-6, 5000)
# 50000 iterations
# theta_full, iters_full = part3(1e-5, 1e-6, 50000)
# Get required actors' image validation data
x_valid, y_valid = dataExtraction.prepare_training_data_label_by_actor_order(
im_data_validation, [3, 5], 10)
# Add constant values for each image data in x_valid
x_valid = np.concatenate(
(x_valid, np.ones([x_valid.shape[0], 1])), axis=1) / 255
# Apply hypothesis function
y_hypothesis = lr.hypothesis(theta_full, x_valid)
# Compute accuracy
accuracy = accuracy_compute.accuracy(y_valid, y_hypothesis)
print(accuracy)
# Using two images of Baldwin and Carell
# Get training data, validation data and testing data from part2
im_data_training, im_data_validation, im_data_testing = part2()
y_train = np.array([1, 1, 0, 0])
x_train = im_data_training[3][10]
x_train = np.vstack((x_train, im_data_training[3][11]))
x_train = np.vstack((x_train, im_data_training[5][20]))
x_train = np.vstack((x_train, im_data_training[5][21]))
# Add constant values for each image in x_train
x_train = np.concatenate(
(x_train, np.ones([x_train.shape[0], 1])), axis=1) / 255
# Theta initialization
theta0 = np.ones(1025) * 0.01
theta_2, costs, iters_2 = lr.gradient_descent(
lr.quadratic_cost_function, lr.derivative_quadratic_cost_function,
x_train, y_train, theta0, 1e-5, 1e-6, 50)
# Show image of theta
new_theta_full = np.reshape(theta_full[:1024], (32, 32))
imshow(new_theta_full, cmap="RdBu", interpolation="spline16")
show()
new_theta_2 = np.reshape(theta_2[:1024], (32, 32))
imshow(new_theta_2, cmap="RdBu", interpolation="spline16")
show()
def part5(alpha, EPS, max_iters):
'''
Plot the performance of the classifiers on the training and validation sets vs the size of the training set.
:param alpha: alpha
:param EPS: epsilon
:param max_iters: maximum iterations
:return: void
'''
i = 0
accuracy_list = []
no_of_images = [10, 20, 30, 40, 50, 60, 70]
while i < 7:
# Get training data, validation data and testing data from part2
im_data_training, im_data_validation, im_data_testing = part2()
# Get required actors' image training data
# Male as 0, female as 1
x_train, y_train = dataExtraction.prepare_training_data_label_by_gender(
im_data_training, [0, 1, 2, 3, 4, 5], [1, 1, 1, 0, 0, 0],
no_of_images[i])
# Add constant values for each image data in x_train
x_train = np.concatenate(
(x_train, np.ones([x_train.shape[0], 1])), axis=1) / 255
# Theta initialization (1024 plus a constant theta)
theta0 = np.ones(1025) * 0.01
# Train classifiers
theta, costs, iters = lr.gradient_descent(
lr.quadratic_cost_function, lr.derivative_quadratic_cost_function,
x_train, y_train, theta0, alpha, EPS, max_iters)
# Get required actors' image validation data
# Male as 0, female as 1
x_valid, y_valid = dataExtraction.prepare_training_data_label_by_gender(
im_data_validation, [0, 1, 2, 3, 4, 5], [1, 1, 1, 0, 0, 0], 10)
# Add constant values for each image data in x_valid
x_valid = np.concatenate(
(x_valid, np.ones([x_valid.shape[0], 1])), axis=1) / 255
# Apply hypothesis function
y_hypothesis = lr.hypothesis(theta, x_valid)
# Compute accuracy
accuracy = accuracy_compute.accuracy(y_valid, y_hypothesis)
accuracy_list.append(accuracy)
i = i + 1
figure(1)
plot(no_of_images, accuracy_list)
xlabel('number of training images for each actor')
ylabel('classifier accuracy')
show()