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
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
|
#!/usr/bin/env python
# Author: Vasil Zlatanov, Nunzio Pucci
# EE4 Pattern Recognition coursework
#
# usage: part2.py [-h] [-t] [-cm] [-km] [-ma] [-e] [-r] [-ka RERANKA]
# [-kb RERANKB] [-v]
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import sys
import random
import os
import json
import scipy.io
from random import randint
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neighbors import DistanceMetric
from sklearn.cluster import KMeans
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
from timeit import default_timer as timer
from scipy.spatial.distance import cdist
from rerank import re_ranking
parser = argparse.ArgumentParser()
parser.add_argument("-t", "--test", help="Use test data instead of query", action='store_true')
parser.add_argument("-cm", "--conf_mat", help="Show visual confusion matrix", action='store_true')
parser.add_argument("-km", "--kmean", help="Perform Kmeans", action='store_true', default=0)
parser.add_argument("-ma", "--mahalanobis", help="Perform Mahalanobis Distance metric", action='store_true', default=0)
parser.add_argument("-e", "--euclidean", help="Standard euclidean", action='store_true', default=0)
parser.add_argument("-r", "--rerank", help="Use k-reciprocal rernaking", action='store_true')
parser.add_argument("-ka", "--reranka", help="Parameter 1 for Rerank", type=int, default = 20)
parser.add_argument("-kb", "--rerankb", help="Parameter 2 for rerank", type=int, default = 6)
parser.add_argument("-n", "--neighbors", help="Number of neighbors", type=int, default = 1)
parser.add_argument("-v", "--verbose", help="Use verbose output", action='store_true')
parser.add_argument("-s", "--showrank", help="Save ranklist pic id in a txt file", type=int, default = 0)
parser.add_argument("-2", "--graphspace", help="Graph space", action='store_true', default=0)
parser.add_argument("-1", "--norm", help="Normalized features", action='store_true', default=0)
args = parser.parse_args()
def verbose(*text):
if args.verbose:
print(text)
#prob query, gal train
def draw_results(test_label, pred_label):
acc_sc = accuracy_score(test_label, pred_label)
cm = confusion_matrix(test_label, pred_label)
print('Accuracy: ', acc_sc)
if (args.conf_mat):
plt.matshow(cm, cmap='Blues')
plt.colorbar()
plt.ylabel('Actual')
plt.xlabel('Predicted')
plt.show()
return
def test_model(gallery_data, probe_data, gallery_label, probe_label, gallery_cam, probe_cam, showfiles_train, showfiles_test, args):
verbose("probe shape:", probe_data.shape)
verbose("gallery shape:", gallery_data.shape)
if args.rerank:
distances = re_ranking(probe_data, gallery_data,
args.reranka ,args.rerankb , 0.3,
MemorySave = False, Minibatch = 2000)
else:
if args.mahalanobis:
# metric = 'jaccard' is also valid
covmat = LA.inv(np.cov(gallery_data))
distances = np.zeros((probe_label.size, gallery_label.size))
for i in range(probe_label.size):
print('Mahalanobis step ', i, '/', probe_label.size)
distances [i] = cdist(probe_data[i].reshape((1,2048)), gallery_data, 'mahalanobis', VI = covmat)
else:
distances = cdist(probe_data, gallery_data, 'euclidean')
ranklist = np.argsort(distances, axis=1)
target_pred = np.zeros(ranklist.shape[0])
nneighbors = np.zeros((ranklist.shape[0],args.neighbors))
nnshowrank = (np.zeros((ranklist.shape[0],args.neighbors))).astype(object)
for probe_idx in range(probe_data.shape[0]):
row = ranklist[probe_idx]
n = 0
q = 0
while (q < args.neighbors):
while (probe_cam[probe_idx] == gallery_cam[row[n]] and
probe_label[probe_idx] == gallery_label[row[n]]):
n += 1
nneighbors[probe_idx][q] = gallery_label[row[n]]
nnshowrank[probe_idx][q] = showfiles_train[row[n]] #
q += 1
n += 1
if (args.neighbors) and (probe_label[probe_idx] in nneighbors[probe_idx]):
target_pred[probe_idx] = probe_label[probe_idx]
else:
target_pred[probe_idx] = nneighbors[probe_idx][0]
if (args.showrank):
with open("ranklist.txt", "w") as text_file:
text_file.write(np.array2string(nnshowrank[:args.showrank]))
with open("query.txt", "w") as text_file:
text_file.write(np.array2string(showfiles_test[:args.showrank]))
if args.graphspace:
# Colors for distinct individuals
cols = ['#{:06x}'.format(randint(0, 0xffffff)) for i in range(1467)]
gallery_label_tmp = np.subtract(gallery_label, 1)
pltCol = [cols[int(k)] for k in gallery_label_tmp]
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(gallery_data[:, 0], gallery_data[:, 1], gallery_data[:, 2], marker='o', color=pltCol)
plt.show()
return target_pred
def main():
mat = scipy.io.loadmat('data/cuhk03_new_protocol_config_labeled.mat')
camId = mat['camId']
filelist = mat['filelist']
labels = mat['labels']
gallery_idx = mat['gallery_idx'] - 1
query_idx = mat['query_idx'] - 1
train_idx = mat['train_idx'] - 1
with open("data/feature_data.json", "r") as read_file:
feature_vectors = np.array(json.load(read_file))
gallery_idx = gallery_idx.reshape(gallery_idx.shape[0])
if args.test:
query_idx = train_idx.reshape(train_idx.shape[0])
else:
query_idx = query_idx.reshape(query_idx.shape[0])
camId = camId.reshape(camId.shape[0])
showfiles_train = filelist[gallery_idx]
showfiles_test = filelist[query_idx]
train_data = feature_vectors[gallery_idx]
test_data = feature_vectors[query_idx]
train_label = labels[gallery_idx]
test_label = labels[query_idx]
train_cam = camId[gallery_idx]
test_cam = camId[query_idx]
if (args.norm):
train_data = np.divide(train_data,LA.norm(train_data, axis=0))
test_data = np.divide(test_data, LA.norm(test_data, axis=0))
if(args.kmean):
gallery1 = []
gallery2 = []
gallery1lab = []
gallery2lab = []
for i in range(gallery_idx.size):
if camId[gallery_idx[i]] == 1:
gallery1.append(feature_vectors[gallery_idx[i]])
gallery1lab.append(labels[gallery_idx[i]])
else:
gallery2.append(feature_vectors[gallery_idx[i]])
gallery2lab.append(labels[gallery_idx[i]])
train1 = np.array(gallery1)
train2 = np.array(gallery2)
tlabel1 = np.array(gallery1lab)
tlabel2 = np.array(gallery2lab)
km_train_data_1 = KMeans(n_clusters=int(np.max(labels)),random_state=0).fit(train1)
km_train_data_2 = KMeans(n_clusters=int(np.max(labels)),random_state=0).fit(train2)
###REMAP LABELS
km_labels_1 = np.zeros(int(np.max(labels))) # clusters size
km_labels_2 = np.zeros(int(np.max(labels)))
km_idx_1 = km_train_data_1.labels_
for i in range(np.max(labels)):
class_vote = np.zeros(np.max(labels))
for q in range(km_idx_1.size):
if km_idx_1[q]==i:
class_vote[int(tlabel1[q])-1] += 1
km_labels_1[i] = np.argmax(class_vote) + 1
km_idx_2 = km_train_data_2.labels_
for i in range(np.max(labels)):
class_vote = np.zeros(np.max(labels))
for q in range(km_idx_2.size):
if km_idx_2[q]==i:
class_vote[int(tlabel2[q])-1] += 1
km_labels_2[i] = np.argmax(class_vote) + 1
#MERGE CLUSTERS
cl = []
cllab = []
clcam = []
clustercam1 = np.ones(km_labels_1.size)
clustercam2 = np.add(np.ones(km_labels_2.size), 1)
for i in range(km_labels_1.size):
cl.append(km_train_data_1.cluster_centers_[i])
cllab.append(km_labels_1[i])
clcam.append(clustercam1[i])
for i in range(km_labels_2.size):
cl.append(km_train_data_2.cluster_centers_[i])
cllab.append(km_labels_2[i])
clcam.append(clustercam2[i])
cluster = np.array(cl)
clusterlabel = np.array(cllab)
clustercam = np.array(clcam)
target_pred = test_model(cluster, test_data, clusterlabel, test_label, clustercam, test_cam, showfiles_train, showfiles_test, args)
draw_results(test_label, target_pred)
else:
target_pred = test_model(train_data, test_data, train_label, test_label, train_cam, test_cam, showfiles_train, showfiles_test, args)
draw_results(test_label, target_pred)
if __name__ == "__main__":
main()
|
