-
Notifications
You must be signed in to change notification settings - Fork 0
/
testing_model.py
160 lines (94 loc) · 4.25 KB
/
testing_model.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
#!/usr/bin/env python
# coding: utf-8
# In[3]:
import sys
sys.path.append("/opt/tf_model/research")
sys.path.append("/opt/tf_model/research/object_detection")
# In[4]:
import os
import cv2
import numpy as np
import tensorflow as tf
from utils import label_map_util
from utils import visualization_utils as vis_util
# In[ ]:
# In[5]:
CWD_PATH = os.getcwd()
MODEL_NAME = 'ssd_mobilenet_v1_coco_2017_11_17'
PATH_TO_CKPT = os.path.join( CWD_PATH, MODEL_NAME, 'frozen_inference_graph.pb')
# In[6]:
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join(CWD_PATH, 'training', 'labelmap.pbtxt')
NUM_CLASSES = 90
# In[ ]:
# In[ ]:
# In[5]:
def detect_objects(image_np, sess, detection_graph):
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image_np, axis=0)
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
scores = detection_graph.get_tensor_by_name('detection_scores:0')
classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
t1 = cv2.getTickCount()
# Actual detection.
(boxes, scores, classes, num_detections) = sess.run(
[boxes, scores, classes, num_detections],
feed_dict={image_tensor: image_np_expanded})
t2 = cv2.getTickCount()
print((t2 - t1) / cv2.getTickFrequency())
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8)
return image_np
if __name__ == '__main__':
# This is needed since the notebook is stored in the object_detection folder.
video_capture = cv2.VideoCapture(0)
if not video_capture.isOpened():
print('No video camera found')
exit()
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(
label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
# Definite input and output Tensors for detection_graph
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
while True:
ret, frame = video_capture.read()
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
result_rgb = detect_objects(frame_rgb, sess, detection_graph)
result_bgr = cv2.cvtColor(result_rgb, cv2.COLOR_RGB2BGR)
cv2.imshow('Video', result_bgr)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
video_capture.release()
cv2.destroyAllWindows()
# In[16]:
# In[ ]:
# In[ ]: