-
Notifications
You must be signed in to change notification settings - Fork 0
/
yolo.py
180 lines (147 loc) · 6.49 KB
/
yolo.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
174
175
176
177
178
179
180
import os
import numpy as np
import copy
import colorsys
from timeit import default_timer as timer
from keras import backend as K
from keras.models import load_model
from keras.layers import Input
from PIL import Image, ImageFont, ImageDraw
from nets.yolo3 import yolo_body, yolo_eval
from utils.utils import letterbox_image
from config.configs import CONFIG
import tensorflow as tf
# remember add this code to avoid some bugs
config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True))
sess = tf.Session(config=config)
class YOLO(object):
_defaults = {
"model_path": CONFIG.PREDICT.WEIGHTS,
"anchors_path": CONFIG.PREDICT.ANCHOR_PATH,
"classes_path": CONFIG.PREDICT.CLASS_PATH,
"score": CONFIG.PREDICT.SCORE,
"iou": CONFIG.PREDICT.IOU,
"model_image_size": CONFIG.PREDICT.RESOLUTION,
"max_boxes": CONFIG.PREDICT.MAX_BOXES
}
@classmethod
def get_defaults(cls, n):
if n in cls._defaults:
return cls._defaults[n]
else:
return "Unrecognized attribute name '" + n + "'"
def __init__(self, **kwargs):
# update dict of YOLO class
self.__dict__.update(self._defaults)
self.class_names = self._get_class()
self.anchors = self._get_anchors()
self.sess = K.get_session()
self.boxes, self.scores, self.classes = self.generate()
def _get_class(self):
classes_path = os.path.expanduser(self.classes_path)
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
def _get_anchors(self):
anchors_path = os.path.expanduser(self.anchors_path)
with open(anchors_path) as f:
anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
return np.array(anchors).reshape(-1, 2)
def generate(self):
model_path = os.path.expanduser(self.model_path)
assert model_path.endswith('.h5'), 'Keras model or weights must be a .h5 file.'
num_anchors = len(self.anchors)
num_classes = len(self.class_names)
try:
self.yolo_model = load_model(model_path, compile=False)
except:
self.yolo_model = yolo_body(Input(shape=(None, None, 3)), num_anchors // 3, num_classes)
self.yolo_model.load_weights(self.model_path)
else:
assert self.yolo_model.layers[-1].output_shape[-1] == \
num_anchors / len(self.yolo_model.output) * (num_classes + 5), \
'Mismatch between model and given anchor and class sizes'
print('{} model, anchors, and classes loaded.'.format(model_path))
# draw rectangles
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
np.random.seed(10101)
np.random.shuffle(self.colors)
np.random.seed(None)
self.input_image_shape = K.placeholder(shape=(2,))
boxes, scores, classes = yolo_eval(self.yolo_model.output,
self.anchors,
num_classes,
self.input_image_shape,
max_boxes=self.max_boxes,
score_threshold=self.score,
iou_threshold=self.iou)
return boxes, scores, classes
def detect_image(self, image):
start = timer()
# convert img_size to input_size
new_image_size = (self.model_image_size[0], self.model_image_size[1])
boxed_image = letterbox_image(image, new_image_size)
image_data = np.array(boxed_image, dtype='float32')
image_data /= 255.
image_data = np.expand_dims(image_data, 0)
# sess.run
out_boxes, out_scores, out_classes = self.sess.run(
[self.boxes, self.scores, self.classes],
feed_dict={
self.yolo_model.input: image_data,
self.input_image_shape: [image.size[1], image.size[0]],
K.learning_phase(): 0
})
# print(out_scores)
# print(out_boxes)
print('Found {} boxes for {}'.format(len(out_boxes), 'img'))
# starting draw bounding boxes
font = ImageFont.truetype(font='font/simhei.ttf',
size=np.floor(2e-2 * image.size[1] + 0.5).astype('int32'))
# thickness of bounding box and this thickness is changing according to img_size
thickness = (image.size[0] + image.size[1]) // 500
for i, c in list(enumerate(out_classes)):
predicted_class = self.class_names[c]
box = out_boxes[i]
score = out_scores[i]
top, left, bottom, right = box
top = top - 5
left = left - 5
bottom = bottom + 5
right = right + 5
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
right = min(image.size[0], np.floor(right + 0.5).astype('int32'))
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
label = label.encode('utf-8')
print(label)
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
for i in range(thickness):
draw.rectangle([left + i, top + i, right - i, bottom - i],
outline=self.colors[c])
draw.rectangle([tuple(text_origin), tuple(text_origin + label_size)],
fill=self.colors[c])
draw.text(text_origin, str(label, 'UTF-8'), fill=(0, 0, 0), font=font)
del draw
end = timer()
print('detect time:', end - start)
return image
def close_session(self):
self.sess.close()
if __name__ == '__main__':
yolo = YOLO()
image = Image.open('./img/kite.jpg')
img = yolo.detect_image(image)
img.show()