def toyExample():
mat = scipy.io.loadmat('../data/toy_data.mat')
data = mat['toy_data']
# TODO: Train PCA
pca = PCA(-1)
pca.train(data)
print("Variance of the data")
# TODO 1.2: Compute data variance to the S vector computed by the PCA
data_variance = np.var(data, axis=1)
print(data_variance)
print(np.power(pca.S, 2) / data.shape[1])
# TODO 1.3: Compute data variance for the projected data (into 1D) to the S vector computed by the PCA
Xout = pca.project(data, 1)
print("Variance of the projected data")
data_variance = np.var(Xout, axis=1)
print(data_variance)
print(np.power(pca.S[0], 2) / data.shape[1])
plt.figure()
plt.title('PCA plot')
plt.subplot(1, 2, 1) # Visualize given data and principal components
# TODO 1.1: Plot original data (hint, use the plot_pca function
pca.plot_pca(data)
plt.subplot(1, 2, 2)
# TODO 1.3: Plot data projected into 1 dimension
pca.S[1] = 0
pca.plot_pca(Xout)
plt.show()
gallery_labels = labels[gallery_idxs - 1]
# num_of_clusters_arr = [100, 200, 300, 400, 500, 600, 700, 800, 900, 1000]
num_of_clusters = 700
n = 10
# Compute K-Means baseline solution
print("-----Baseline K-Means-----")
compute_k_mean(num_of_clusters, query_features, gallery_features,
gallery_labels)
# Compute PCA result
print("\n-----PCA------")
pca = PCA(original_train_features, M=500)
pca.fit()
pca_query_features = pca.project(query_features)
pca_gallery_features = pca.project(gallery_features)
compute_k_mean(num_of_clusters, pca_query_features, pca_gallery_features,
gallery_labels)
# Compute LMNN (Large Margin Nearest Neighbour) Learning
print("\n-----LMNN------")
lmnn = LMNN(k=5,
max_iter=20,
use_pca=False,
convergence_tol=1e-6,
learn_rate=1e-6,
verbose=True)
lmnn.fit(original_train_features, original_train_labels)
transformed_query_features = lmnn.transform(query_features)
transformed_gallery_features = lmnn.transform(gallery_features)
def faceRecognition():
'''
Train PCA with with 25 components
Project each face from 'novel' into PCA space to obtain feature coordinates
Find closest face in 'gallery' according to:
- Euclidean distance
- Mahalanobis distance
Redo with different PCA dimensionality
What is the effect of reducing the dimensionality?
What is the effect of different similarity measures?
'''
numOfPrincipalComponents = 25
# TODO: Train a PCA on the provided face images
pca = PCA(numOfPrincipalComponents)
(X, data_labels, gall_faces) = data_matrix()
pca.train(X)
alphagal = pca.to_pca(X)
# TODO: Plot the variance of each principal component - use a simple plt.plot()
f = plt.figure(1)
plt.plot(np.var(alphagal, 1, dtype=np.float64))
f.show()
# TODO: Implement face recognition
(novel, novel_labels, nov_faces) = load_novel()
alphanov = pca.to_pca(novel)
matches_e = []
matches_m = []
invS = np.diag(1. / pca.S)
for i in range(alphanov.shape[1]):
lowest_e = (sys.maxsize, 0)
lowest_m = (sys.maxsize, 0)
for j in range(alphagal.shape[1]):
euclidean = euclideanDistance(alphanov[:, i], alphagal[:, j])
if euclidean < lowest_e[0]:
lowest_e = euclidean, j
maha = mahalanobisDistance(alphanov[:, i], alphagal[:, j], invS)
if maha < lowest_m[0]:
lowest_m = maha, j
matches_e.append((i, lowest_e[1]))
matches_m.append((i, lowest_m[1]))
print(matches_e)
print(matches_m)
correct_m = 0
correct_e = 0
correct_classified = 0
correct_partner = 0
wrong_classified = 0
wrong_partner = 0
for x in range(len(matches_e)):
if data_labels[matches_e[x][0]] == novel_labels[matches_e[x][1]]:
correct_e += 1
correct_classified = x
correct_partner = matches_e[x][1]
else:
wrong_classified = x
wrong_partner = matches_e[x][1]
if data_labels[matches_m[x][0]] == novel_labels[matches_m[x][1]]:
correct_m += 1
print("Correct Euclidian Classification in percent: {}".format(
correct_e / len(matches_e) * 100))
print("Correct Mahalanobis Classification in percent: {}".format(
correct_m / len(matches_m) * 100))
# TODO: Visualize some of the correctly and wrongly classified images (see example in exercise sheet)
# Show correct classified
fig = plt.figure(2)
columns = 3
rows = 2
titles = ("correct test", "wrong test", "projected test", "correct train",
"wrong train", "projected train")
# plt.title(titles[i])
# correct
sub = fig.add_subplot(rows, columns, 1)
sub.set_title("Novel to test")
sub.set_ylabel("Correct Classified")
plt.imshow(nov_faces.item(correct_classified)[1], cmap='gray')
sub = fig.add_subplot(rows, columns, 2)
sub.set_title("Closest from training")
plt.imshow(gall_faces.item(correct_partner)[1], cmap='gray')
sub = fig.add_subplot(rows, columns, 3)
sub.set_title("Novel projected")
correct_projected = pca.project(
novel, numOfPrincipalComponents)[:, correct_classified].reshape(
gall_faces.item(correct_partner)[1].shape)
plt.imshow(correct_projected, cmap='gray')
# wrong
sub = fig.add_subplot(rows, columns, 4)
sub.set_title("Novel to test")
sub.set_ylabel("Wrong Classified")
plt.imshow(nov_faces.item(wrong_classified)[1], cmap='gray')
sub = fig.add_subplot(rows, columns, 5)
sub.set_title("Closest from training")
plt.imshow(gall_faces.item(wrong_partner)[1], cmap='gray')
sub = fig.add_subplot(rows, columns, 6)
sub.set_title("Novel projected")
wrong_projected = pca.project(
novel, numOfPrincipalComponents)[:, wrong_classified].reshape(
gall_faces.item(wrong_partner)[1].shape)
plt.imshow(wrong_projected, cmap='gray')
fig.show()
