This repository has been archived by the owner on Oct 18, 2022. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 36
/
generator.py
173 lines (163 loc) · 6.42 KB
/
generator.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
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
import numpy as np
from random import shuffle
from scipy.misc import imread
from scipy.misc import imresize
from keras.applications.imagenet_utils import preprocess_input
class Generator(object):
def __init__(self, gt, bbox_util,
batch_size, path_prefix,
train_keys, val_keys, image_size,
saturation_var=0.5,
brightness_var=0.5,
contrast_var=0.5,
lighting_std=0.5,
hflip_prob=0.5,
vflip_prob=0.5,
do_crop=True,
crop_area_range=[0.75, 1.0],
aspect_ratio_range=[3./4., 4./3.]):
self.gt = gt
self.bbox_util = bbox_util
self.batch_size = batch_size
self.path_prefix = path_prefix
self.train_keys = train_keys
self.val_keys = val_keys
self.train_batches = len(train_keys)
self.val_batches = len(val_keys)
self.image_size = image_size
self.color_jitter = []
if saturation_var:
self.saturation_var = saturation_var
self.color_jitter.append(self.saturation)
if brightness_var:
self.brightness_var = brightness_var
self.color_jitter.append(self.brightness)
if contrast_var:
self.contrast_var = contrast_var
self.color_jitter.append(self.contrast)
self.lighting_std = lighting_std
self.hflip_prob = hflip_prob
self.vflip_prob = vflip_prob
self.do_crop = do_crop
self.crop_area_range = crop_area_range
self.aspect_ratio_range = aspect_ratio_range
def grayscale(self, rgb):
return rgb.dot([0.299, 0.587, 0.114])
def saturation(self, rgb):
gs = self.grayscale(rgb)
alpha = 2 * np.random.random() * self.saturation_var
alpha += 1 - self.saturation_var
rgb = rgb * alpha + (1 - alpha) * gs[:, :, None]
return np.clip(rgb, 0, 255)
def brightness(self, rgb):
alpha = 2 * np.random.random() * self.brightness_var
alpha += 1 - self.saturation_var
rgb = rgb * alpha
return np.clip(rgb, 0, 255)
def contrast(self, rgb):
gs = self.grayscale(rgb).mean() * np.ones_like(rgb)
alpha = 2 * np.random.random() * self.contrast_var
alpha += 1 - self.contrast_var
rgb = rgb * alpha + (1 - alpha) * gs
return np.clip(rgb, 0, 255)
def lighting(self, img):
cov = np.cov(img.reshape(-1, 3) / 255.0, rowvar=False)
eigval, eigvec = np.linalg.eigh(cov)
noise = np.random.randn(3) * self.lighting_std
noise = eigvec.dot(eigval * noise) * 255
img += noise
return np.clip(img, 0, 255)
def horizontal_flip(self, img, y):
if np.random.random() < self.hflip_prob:
img = img[:, ::-1]
y[:, [0, 2]] = 1 - y[:, [2, 0]]
return img, y
def vertical_flip(self, img, y):
if np.random.random() < self.vflip_prob:
img = img[::-1]
y[:, [1, 3]] = 1 - y[:, [3, 1]]
return img, y
def random_sized_crop(self, img, targets):
img_w = img.shape[1]
img_h = img.shape[0]
img_area = img_w * img_h
random_scale = np.random.random()
random_scale *= (self.crop_area_range[1] -
self.crop_area_range[0])
random_scale += self.crop_area_range[0]
target_area = random_scale * img_area
random_ratio = np.random.random()
random_ratio *= (self.aspect_ratio_range[1] -
self.aspect_ratio_range[0])
random_ratio += self.aspect_ratio_range[0]
w = np.round(np.sqrt(target_area * random_ratio))
h = np.round(np.sqrt(target_area / random_ratio))
if np.random.random() < 0.5:
w, h = h, w
w = min(w, img_w)
w_rel = w / img_w
w = int(w)
h = min(h, img_h)
h_rel = h / img_h
h = int(h)
x = np.random.random() * (img_w - w)
x_rel = x / img_w
x = int(x)
y = np.random.random() * (img_h - h)
y_rel = y / img_h
y = int(y)
img = img[y:y+h, x:x+w]
new_targets = []
for box in targets:
cx = 0.5 * (box[0] + box[2])
cy = 0.5 * (box[1] + box[3])
if (x_rel < cx < x_rel + w_rel and
y_rel < cy < y_rel + h_rel):
xmin = (box[0] - x_rel) / w_rel
ymin = (box[1] - y_rel) / h_rel
xmax = (box[2] - x_rel) / w_rel
ymax = (box[3] - y_rel) / h_rel
xmin = max(0, xmin)
ymin = max(0, ymin)
xmax = min(1, xmax)
ymax = min(1, ymax)
box[:4] = [xmin, ymin, xmax, ymax]
new_targets.append(box)
new_targets = np.asarray(new_targets).reshape(-1, targets.shape[1])
return img, new_targets
def generate(self, train=True):
while True:
if train:
shuffle(self.train_keys)
keys = self.train_keys
else:
shuffle(self.val_keys)
keys = self.val_keys
inputs = []
targets = []
for key in keys:
img_path = self.path_prefix + key
img = imread(img_path).astype('float32')
y = self.gt[key].copy()
if train and self.do_crop:
img, y = self.random_sized_crop(img, y)
img = imresize(img, self.image_size).astype('float32')
if train:
shuffle(self.color_jitter)
for jitter in self.color_jitter:
img = jitter(img)
if self.lighting_std:
img = self.lighting(img)
if self.hflip_prob > 0:
img, y = self.horizontal_flip(img, y)
if self.vflip_prob > 0:
img, y = self.vertical_flip(img, y)
y = self.bbox_util.assign_boxes(y)
inputs.append(img)
targets.append(y)
if len(targets) == self.batch_size:
tmp_inp = np.array(inputs)
tmp_targets = np.array(targets)
inputs = []
targets = []
yield preprocess_input(tmp_inp), tmp_targets