/
detection_model.py
99 lines (77 loc) · 3.77 KB
/
detection_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
# Copyright (C) 2018-2019 David Thompson
#
# This file is part of Grassland
#
# It is subject to the license terms in the LICENSE file found in the top-level
# directory of this distribution.
#
# No part of Grassland, including this file, may be copied, modified,
# propagated, or distributed except according to the terms contained in the
# LICENSE file.
import os
import numpy as np
import operator
import tensorflow as tf
import settings
import time
class DetectionModel:
def __init__(self, path_to_ckpt):
# Parts of this "__init__" "method adapted from https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb
self.path_to_ckpt = path_to_ckpt
self.detection_graph = tf.Graph()
with self.detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(self.path_to_ckpt, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
self.default_graph = self.detection_graph.as_default()
self.sess = tf.Session(graph=self.detection_graph)
# Definite input and output Tensors for detection_graph
self.image_tensor = self.detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
self.detection_boxes = self.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.
self.detection_scores = self.detection_graph.get_tensor_by_name('detection_scores:0')
self.detection_classes = self.detection_graph.get_tensor_by_name('detection_classes:0')
self.num_detections = self.detection_graph.get_tensor_by_name('num_detections:0')
def predict(self, image):
# Code adapted from https://gist.github.com/madhawav/1546a4b99c8313f06c0b2d7d7b4a09e2
# Expand dimensions since the trained_model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image, axis=0)
# Actual detection.
start_time = time.time()
(boxes, scores, classes, num) = self.sess.run(
[self.detection_boxes, self.detection_scores, self.detection_classes, self.num_detections],
feed_dict={self.image_tensor: image_np_expanded})
end_time = time.time()
print("Elapsed Time:", end_time-start_time)
im_height, im_width,_ = image.shape
''' Commented out to return normalized coordinates instead
# boxes_list = [None for i in range(boxes.shape[1])]
# for i in range(boxes.shape[1]):
# boxes_list[i] = (int(boxes[0,i,0] * im_height),
# int(boxes[0,i,1]*im_width),
# int(boxes[0,i,2] * im_height),
# int(boxes[0,i,3]*im_width))
# return boxes_list, scores[0].tolist(), [int(x) for x in classes[0].tolist()], int(num[0])
'''
output_dict = {}
output_dict['detection_boxes'] = boxes[0].tolist()
output_dict['detection_scores'] = scores[0].tolist()
output_dict['detection_classes'] = [int(x) for x in classes[0].tolist()]
output_dict['num_detections'] = int(num[0])
return output_dict
def __enter__(self):
# for using with "with" block
return self
def __exit__(self, type_, value, traceback):
# close session at the end of "with" block
self.destroy()
def destroy(self):
'''
Close TensorFlow session
'''
self.sess.close()
self.default_graph.close()