-
Notifications
You must be signed in to change notification settings - Fork 1
/
test.py
215 lines (176 loc) · 8.2 KB
/
test.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
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
import tensorflow as tf
import datetime
import os
import argparse
from yolo_models import Original_Yolo_Model
from timer import Timer
from pascal_voc import pascal_voc
import skvideo.io
import cv2
import numpy as np
class Detector(object):
def __init__(self, net, weight_file):
self.net = net
self.weights_file = weight_file
self.classes = CLASSES = ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus',
'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse',
'motorbike', 'person', 'pottedplant', 'sheep', 'sofa',
'train', 'tvmonitor']
self.num_class = len(self.classes)
self.image_size = 448
self.cell_size = 7
self.boxes_per_cell = 2
self.threshold = 0.2
self.iou_threshold = 0.5
self.boundary1 = self.cell_size * self.cell_size * self.num_class
self.boundary2 = self.boundary1 + self.cell_size * self.cell_size * self.boxes_per_cell
self.sess = tf.Session()
self.sess.run(tf.global_variables_initializer())
print 'Restoring weights from: ' + self.weights_file
self.saver = tf.train.Saver()
self.saver.restore(self.sess, self.weights_file)
def draw_result(self, img, result):
for i in range(len(result)):
x = int(result[i][1])
y = int(result[i][2])
w = int(result[i][3] / 2)
h = int(result[i][4] / 2)
cv2.rectangle(img, (x - w, y - h), (x + w, y + h), (0, 255, 0), 2)
cv2.rectangle(img, (x - w, y - h - 20),
(x + w, y - h), (125, 125, 125), -1)
cv2.putText(img, result[i][0] + ' : %.2f' % result[i][5], (x - w + 5, y - h - 7), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 1, cv2.LINE_AA)
def detect(self, img):
img_h, img_w, _ = img.shape
inputs = cv2.resize(img, (self.image_size, self.image_size))
inputs = cv2.cvtColor(inputs, cv2.COLOR_BGR2RGB).astype(np.float32)
inputs = (inputs / 255.0) * 2.0 - 1.0
inputs = np.reshape(inputs, (1, self.image_size, self.image_size, 3))
result = self.detect_from_cvmat(inputs)[0]
for i in range(len(result)):
result[i][1] *= (1.0 * img_w / self.image_size)
result[i][2] *= (1.0 * img_h / self.image_size)
result[i][3] *= (1.0 * img_w / self.image_size)
result[i][4] *= (1.0 * img_h / self.image_size)
return result
def detect_from_cvmat(self, inputs):
net_output = self.sess.run(self.net.logits,
feed_dict={self.net.images: inputs})
results = []
for i in range(net_output.shape[0]):
results.append(self.interpret_output(net_output[i]))
return results
def interpret_output(self, output):
probs = np.zeros((self.cell_size, self.cell_size,
self.boxes_per_cell, self.num_class))
class_probs = np.reshape(output[0:self.boundary1], (self.cell_size, self.cell_size, self.num_class))
scales = np.reshape(output[self.boundary1:self.boundary2], (self.cell_size, self.cell_size, self.boxes_per_cell))
boxes = np.reshape(output[self.boundary2:], (self.cell_size, self.cell_size, self.boxes_per_cell, 4))
offset = np.transpose(np.reshape(np.array([np.arange(self.cell_size)] * self.cell_size * self.boxes_per_cell),
[self.boxes_per_cell, self.cell_size, self.cell_size]), (1, 2, 0))
boxes[:, :, :, 0] += offset
boxes[:, :, :, 1] += np.transpose(offset, (1, 0, 2))
boxes[:, :, :, :2] = 1.0 * boxes[:, :, :, 0:2] / self.cell_size
boxes[:, :, :, 2:] = np.square(boxes[:, :, :, 2:])
boxes *= self.image_size
for i in range(self.boxes_per_cell):
for j in range(self.num_class):
probs[:, :, i, j] = np.multiply(
class_probs[:, :, j], scales[:, :, i])
filter_mat_probs = np.array(probs >= self.threshold, dtype='bool')
filter_mat_boxes = np.nonzero(filter_mat_probs)
boxes_filtered = boxes[filter_mat_boxes[0],
filter_mat_boxes[1], filter_mat_boxes[2]]
probs_filtered = probs[filter_mat_probs]
classes_num_filtered = np.argmax(filter_mat_probs, axis=3)[filter_mat_boxes[
0], filter_mat_boxes[1], filter_mat_boxes[2]]
argsort = np.array(np.argsort(probs_filtered))[::-1]
boxes_filtered = boxes_filtered[argsort]
probs_filtered = probs_filtered[argsort]
classes_num_filtered = classes_num_filtered[argsort]
for i in range(len(boxes_filtered)):
if probs_filtered[i] == 0:
continue
for j in range(i + 1, len(boxes_filtered)):
if self.iou(boxes_filtered[i], boxes_filtered[j]) > self.iou_threshold:
probs_filtered[j] = 0.0
filter_iou = np.array(probs_filtered > 0.0, dtype='bool')
boxes_filtered = boxes_filtered[filter_iou]
probs_filtered = probs_filtered[filter_iou]
classes_num_filtered = classes_num_filtered[filter_iou]
result = []
for i in range(len(boxes_filtered)):
result.append([self.classes[classes_num_filtered[i]], boxes_filtered[i][0], boxes_filtered[
i][1], boxes_filtered[i][2], boxes_filtered[i][3], probs_filtered[i]])
return result
def iou(self, box1, box2):
tb = min(box1[0] + 0.5 * box1[2], box2[0] + 0.5 * box2[2]) - \
max(box1[0] - 0.5 * box1[2], box2[0] - 0.5 * box2[2])
lr = min(box1[1] + 0.5 * box1[3], box2[1] + 0.5 * box2[3]) - \
max(box1[1] - 0.5 * box1[3], box2[1] - 0.5 * box2[3])
if tb < 0 or lr < 0:
intersection = 0
else:
intersection = tb * lr
return intersection / (box1[2] * box1[3] + box2[2] * box2[3] - intersection)
def camera_detector(self, cap, wait=10):
detect_timer = Timer()
ret, _ = cap.read()
while ret:
ret, frame = cap.read()
detect_timer.tic()
result = self.detect(frame)
detect_timer.toc()
print('Average detecting time: {:.3f}s'.format(detect_timer.average_time))
self.draw_result(frame, result)
cv2.imshow('Camera', frame)
cv2.waitKey(wait)
ret, frame = cap.read()
def image_detector(self, imname, wait=0):
detect_timer = Timer()
image = cv2.imread(imname)
# image = frame
detect_timer.tic()
result = self.detect(image)
detect_timer.toc()
print('Average detecting time: {:.3f}s'.format(detect_timer.average_time))
self.draw_result(image, result)
cv2.imshow('Image', image)
cv2.waitKey(wait)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--weight_dir', default='weights', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = "0"
yolo = Original_Yolo_Model(False)
# print yolo
# exit(0)
weight_file = os.path.join('weights','YOLO_small.ckpt')
# weight_file = os.path.join('/home/vikram_mm/yolo_tensorflow/data/weights/YOLO_small.ckpt')
detector = Detector(yolo, weight_file)
# detect from camera
# cap = cv2.VideoCapture(-1)
# detector.camera_detector(cap)
# detect from image file
print "HERE"
# videogen = skvideo.io.vreader('/home/vikram_mm/yolo_tensorflow/test/videoplayback.mp4')
# for frame in videogen:
# print(frame.shape)
# #frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
# detector.image_detector(frame, wait=40)
# #cv2.imshow('frame',frame)
# # cv2.destroyAllWindows()
# # while(cap.isOpened()):
# ret, frame = cap.read()
# print frame.shape
# for k in ['000138.jpg','000147.jpg','000164.jpg'] :
# imname = '000138.jpg'
# imname = '000147.jpg'
imname = '000164.jpg'
detector.image_detector(imname)
# cap.release()
cv2.destroyAllWindows()
if __name__ == '__main__':
main()