1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
|
#!/usr/bin/env python
# Train a model from sample data
# Author: Vasil Zlatanov, Nunzio Pucci
# EE4 Pattern Recognition coursework
import matplotlib.pyplot as plt
import sys
import random
from random import randint
from sklearn.neighbors import KNeighborsClassifier
from sklearn.decomposition import PCA
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
import argparse
import numpy as np
from numpy import genfromtxt
from numpy import linalg as LA
# subtract the normal face from each row of the face matrix
def normalise_faces(average_face, faces):
faces = np.subtract(faces, np.tile(average_face, (faces.shape[0],1)))
return np.divide(faces.T, np.std(faces.T, axis=0)).T
# Split data into training and testing sets
def test_split(n_faces, raw_faces, split, seed):
random.seed(seed)
n_cases = 52
n_pixels = 2576
raw_faces_split = np.split(raw_faces,n_cases)
n_training_faces = int(round(n_cases*(1 - split)))
n_test_faces = n_cases - n_training_faces
faces_train = np.zeros((n_faces, n_training_faces, n_pixels))
faces_test = np.zeros((n_faces, n_test_faces, n_pixels))
target_train = np.repeat(np.arange(n_faces), n_training_faces)
target_test = np.repeat(np.arange(n_faces), n_test_faces)
for x in range (n_faces):
samples = random.sample(range(n_cases), n_training_faces)
faces_train[x] = [raw_faces[i+n_cases*x] for i in samples]
faces_test[x] = [raw_faces[i+n_cases*x] for i in range (n_cases) if i not in samples]
faces_train = faces_train.reshape(n_faces*n_training_faces, n_pixels)
faces_test = faces_test.reshape(n_faces*n_test_faces, n_pixels)
return faces_train, faces_test, target_train, target_test
# usage: train.py [-h] -i DATA -o MODEL [-m M]
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--data", help="Input CSV file", required=True)
parser.add_argument("-m", "--eigen", help="Number of eigenvalues in model", type=int, default = 10 )
parser.add_argument("-n", "--neighbors", help="How many neighbors to use", type=int, default = 3)
parser.add_argument("-f", "--faces", help="Show faces", type=int, default = 0)
parser.add_argument("-c", "--principal", help="Show principal components", action='store_true')
parser.add_argument("-s", "--seed", help="Seed to use", type=int, default=0)
parser.add_argument("-t", "--split", help="Fractoin of data to use for testing", type=float, default=0.22)
### best split for lda = 22
### best plit for pca = 20
parser.add_argument("-2", "--grapheigen", help="Swow 2D graph of targets versus principal components", action='store_true')
parser.add_argument("-p", "--pca", help="Use PCA", action='store_true')
parser.add_argument("-l", "--lda", help="Use LDA", action='store_true')
parser.add_argument("-r", "--reconstruct", help="Use PCA reconstruction, specify face NR", type=int, default=0)
parser.add_argument("-q", "--pca_r", help="Use Reduced PCA", action='store_true')
args = parser.parse_args()
M = args.eigen
raw_faces = genfromtxt(args.data, delimiter=',')
targets = np.repeat(np.arange(10),52)
n_faces = 10
faces_train, faces_test, target_train, target_test = test_split(n_faces, raw_faces, args.split, args.seed)
# This remove the mean and scales to unit variance
sc = StandardScaler()
#faces_train = sc.fit_transform(faces_train)
#faces_test = sc.transform(faces_test)
raw_faces_train = faces_train
explained_variances = ()
if args.pca or args.pca_r:
# faces_pca containcts the principial components or the M most variant eigenvectors
average_face = np.mean(faces_train, axis=0)
deviations = np.std(faces_train, axis=0)
faces_train = normalise_faces(average_face, faces_train)
faces_test = normalise_faces(average_face, faces_test)
if (args.pca_r):
print('Reduced PCA')
e_vals, e_vecs = LA.eigh(np.dot(faces_train, faces_train.T))
e_vecs = np.dot(faces_train.T, e_vecs)
e_vecs = e_vecs/LA.norm(e_vecs, axis = 0)
else:
print('Standard PCA')
e_vals, e_vecs = LA.eigh(np.cov(faces_train.T))
# e_vecs = normalise_faces(np.mean(e_vecs,axis=0), e_vecs)
# e_vecs = sc.fit_transform(e_vecs)
e_vals = np.flip(e_vals)[:M]
e_vecs = np.fliplr(e_vecs).T[:M]
deviations = np.flip(deviations)
faces_train = np.dot(faces_train, e_vecs.T)
faces_test = np.dot(faces_test, e_vecs.T)
if (args.reconstruct):
rec_vec = np.add(average_face, np.dot(faces_train[args.reconstruct], e_vecs) * deviations)
rec_error = LA.norm(np.subtract(raw_faces_train[args.reconstruct], rec_vec))
print(rec_error)
ar = plt.subplot(2, 1, 1)
ar.imshow(rec_vec.reshape([46,56]).T, cmap = 'gist_gray')
ar = plt.subplot(2, 1, 2)
ar.imshow(raw_faces_train[args.reconstruct].reshape([46,56]).T, cmap = 'gist_gray')
plt.show()
if args.lda or (args.pca and args.lda):
lda = LinearDiscriminantAnalysis(n_components=M)
faces_train = lda.fit_transform(faces_train, target_train)
faces_test = lda.transform(faces_test)
class_means = lda.means_
e_vals = lda.explained_variance_ratio_
if args.faces:
if args.lda:
for i in range (10):
ax = plt.subplot(2, 5, i + 1)
ax.imshow(class_means[i].reshape([46,56]).T)
else:
for i in range(args.faces):
ax = plt.subplot(2, args.faces/2, i + 1)
ax.imshow(e_vecs[i].reshape([46, 56]).T, cmap = 'gist_gray')
plt.show()
if args.principal:
e_vals = np.multiply(np.divide(e_vals, np.sum(e_vals)), 100)
plt.bar(np.arange(M), e_vals[:M])
plt.ylabel('Varaiance ratio (%)');plt.xlabel('Eigenface Number')
plt.show()
if args.grapheigen:
# Colors for distinct individuals
cols = ['#{:06x}'.format(randint(0, 0xffffff)) for i in range(10)]
pltCol = [cols[int(k)] for k in target_train]
plt.scatter(faces_train[:, 0], faces_train[:, 1], color=pltCol)
plt.show()
classifier = KNeighborsClassifier(n_neighbors=args.neighbors)
classifier.fit(faces_train, target_train)
target_pred = classifier.predict(faces_test)
cm = confusion_matrix(target_test, target_pred)
print(cm)
print('Accuracy %fl' % accuracy_score(target_test, target_pred))
|
