-
Notifications
You must be signed in to change notification settings - Fork 8
/
gen_anchors.py
137 lines (104 loc) · 4 KB
/
gen_anchors.py
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
import random
import argparse
import numpy as np
from preprocessing import parse_annotation
import json
argparser = argparse.ArgumentParser()
argparser.add_argument(
'-c',
'--conf',
default='config.json',
help='path to configuration file')
argparser.add_argument(
'-a',
'--anchors',
default=5,
help='number of anchors to use')
def IOU(ann, centroids):
w, h = ann
similarities = []
for centroid in centroids:
c_w, c_h = centroid
if c_w >= w and c_h >= h:
similarity = w*h/(c_w*c_h)
elif c_w >= w and c_h <= h:
similarity = w*c_h/(w*h + (c_w-w)*c_h)
elif c_w <= w and c_h >= h:
similarity = c_w*h/(w*h + c_w*(c_h-h))
else: #means both w,h are bigger than c_w and c_h respectively
similarity = (c_w*c_h)/(w*h)
similarities.append(similarity) # will become (k,) shape
return np.array(similarities)
def avg_IOU(anns, centroids):
n,d = anns.shape
sum = 0.
for i in range(anns.shape[0]):
sum+= max(IOU(anns[i], centroids))
return sum/n
def print_anchors(centroids):
anchors = centroids.copy()
widths = anchors[:, 0]
sorted_indices = np.argsort(widths)
r = "anchors: ["
for i in sorted_indices[:-1]:
r += '%0.2f,%0.2f, ' % (anchors[i,0], anchors[i,1])
#there should not be comma after last anchor, that's why
r += '%0.2f,%0.2f' % (anchors[sorted_indices[-1:],0], anchors[sorted_indices[-1:],1])
r += "]"
print(r)
def run_kmeans(ann_dims, anchor_num):
ann_num = ann_dims.shape[0]
iterations = 0
prev_assignments = np.ones(ann_num)*(-1)
iteration = 0
old_distances = np.zeros((ann_num, anchor_num))
indices = [random.randrange(ann_dims.shape[0]) for i in range(anchor_num)]
centroids = ann_dims[indices]
anchor_dim = ann_dims.shape[1]
while True:
distances = []
iteration += 1
for i in range(ann_num):
d = 1 - IOU(ann_dims[i], centroids)
distances.append(d)
distances = np.array(distances) # distances.shape = (ann_num, anchor_num)
print("iteration {}: dists = {}".format(iteration, np.sum(np.abs(old_distances-distances))))
#assign samples to centroids
assignments = np.argmin(distances,axis=1)
if (assignments == prev_assignments).all() :
return centroids
#calculate new centroids
centroid_sums=np.zeros((anchor_num, anchor_dim), np.float)
for i in range(ann_num):
centroid_sums[assignments[i]]+=ann_dims[i]
for j in range(anchor_num):
centroids[j] = centroid_sums[j]/(np.sum(assignments==j) + 1e-6)
prev_assignments = assignments.copy()
old_distances = distances.copy()
def main(argv):
config_path = args.conf
num_anchors = args.anchors
with open(config_path) as config_buffer:
config = json.loads(config_buffer.read())
train_imgs, train_labels = parse_annotation(config['train']['train_annot_folder'],
config['train']['train_image_folder'],
config['model']['labels'])
grid_w = config['model']['input_size']/32
grid_h = config['model']['input_size']/32
# run k_mean to find the anchors
annotation_dims = []
for image in train_imgs:
cell_w = image['width']/grid_w
cell_h = image['height']/grid_h
for obj in image['object']:
relative_w = (float(obj['xmax']) - float(obj['xmin']))/cell_w
relatice_h = (float(obj["ymax"]) - float(obj['ymin']))/cell_h
annotation_dims.append(tuple(map(float, (relative_w,relatice_h))))
annotation_dims = np.array(annotation_dims)
centroids = run_kmeans(annotation_dims, num_anchors)
# write anchors to file
print('\naverage IOU for', num_anchors, 'anchors:', '%0.2f' % avg_IOU(annotation_dims, centroids))
print_anchors(centroids)
if __name__ == '__main__':
args = argparser.parse_args()
main(args)