forked from wayne-89/tensorWork
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Object_detection_image.py
187 lines (160 loc) · 6.8 KB
/
Object_detection_image.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
# coding=utf-8
######## Image Object Detection Using Tensorflow-trained Classifier #########
#
# Author: Evan Juras
# Date: 1/15/18
# Description:
# This program uses a TensorFlow-trained classifier to perform object detection.
# It loads the classifier uses it to perform object detection on an image.
# It draws boxes and scores around the objects of interest in the image.
## Some of the code is copied from Google's example at
## https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb
## and some is copied from Dat Tran's example at
## https://github.com/datitran/object_detector_app/blob/master/object_detection_app.py
## but I changed it to make it more understandable to me.
# Import packages
import os
import cv2
import numpy as np
import tensorflow as tf
import sys
import json
import ast
import urllib.parse
# import matplotlib
# matplotlib.use('TkAgg')
# import matplotlib.pyplot as plt
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util
# Name of the directory containing the object detection module we're using
MODEL_NAME = 'inference_graph'
IMAGE_NAME = 'test_pot/4.jpg'
# Grab path to current working directory
CWD_PATH = os.getcwd()
IMAGE_SHOW = False
PATH_TO_CKPT = sys.argv[1]
PATH_TO_LABELS = sys.argv[2]
PATH_TO_IMAGE = sys.argv[3]
labelNameMap = {}
# Path to frozen detection graph .pb file, which contains the model that is used
# for object detection.
if PATH_TO_CKPT is None:
PATH_TO_CKPT = os.path.join(CWD_PATH, MODEL_NAME, 'frozen_inference_graph.pb')
# Path to label map file
if PATH_TO_LABELS is None:
PATH_TO_LABELS = os.path.join(CWD_PATH, 'training', 'labelmap.pbtxt')
# Path to image
if PATH_TO_IMAGE is None:
PATH_TO_IMAGE = os.path.join(CWD_PATH, IMAGE_NAME)
# Number of classes the object detector can identify
if sys.argv[4] is None:
NUM_CLASSES = 6
else:
NUM_CLASSES = int(sys.argv[4])
if sys.argv[5] is not None:
loaded = urllib.parse.unquote(sys.argv[5])
loaded = json.loads(loaded)
labelNameMap = loaded
# Load the label map.
# Label maps map indices to category names, so that when our convolution
# network predicts `5`, we know that this corresponds to `king`.
# Here we use internal utility functions, but anything that returns a
# dictionary mapping integers to appropriate string labels would be fine
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)
# Load the Tensorflow model into memory.
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='')
sess = tf.Session(graph=detection_graph)
# Define input and output tensors (i.e. data) for the object detection classifier
# Input tensor is the image
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Output tensors are the detection boxes, scores, and classes
# 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 represents level of confidence for each of the objects.
# The 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')
# Number of objects detected
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
IMAGE_PATHS = []
PATH_TO_IMAGE_DIR = PATH_TO_IMAGE
if not os.path.isfile(PATH_TO_IMAGE):
for filename in os.listdir(PATH_TO_IMAGE):
if filename.lower().endswith((".jpg", ".jpeg", ".png", ".bmp")):
IMAGE_PATHS.append(os.path.join(PATH_TO_IMAGE, filename))
else:
IMAGE_PATHS.append(PATH_TO_IMAGE)
PATH_TO_IMAGE_DIR = os.path.dirname(PATH_TO_IMAGE)
for IMAGE_PATH in IMAGE_PATHS:
# Load image using OpenCV and
# expand image dimensions to have shape: [1, None, None, 3]
# i.e. a single-column array, where each item in the column has the pixel RGB value
print('path####### {0}'.format(IMAGE_PATH))
image = cv2.imread(IMAGE_PATH)
image_expanded = np.expand_dims(image, axis=0)
# Perform the actual detection by running the model with the image as input
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: image_expanded})
# Draw the results of the detection (aka 'visulaize the results')
# print('image params ',labelNameMap,category_index)
for key in category_index:
_label = category_index[key]
_name = _label['name']
if _name in labelNameMap:
_label['name'] = labelNameMap[_name]
print('image params after', category_index)
v_res = vis_util.visualize_boxes_and_labels_on_image_array(
image,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8,
min_score_thresh=0.60)
image_rec_res = []
if len(scores) > 0:
print('v_res 识别数量: ', scores[0])
for idx in range(0, len(scores[0])):
if scores[0][idx] > 0.60:
image_rec_res.append(
{'score': float(scores[0][idx]), 'id': int(classes[0][idx]),
'name': category_index[classes[0][idx]]['name']})
# print('v_res 识别数量: ', scores, classes, num, image_rec_res)
# All the results have been drawn on image. Now display the image.
FULL_NAME = IMAGE_PATH.split("/")
SHOW_NAME = FULL_NAME[-1]
with open(os.path.join(PATH_TO_IMAGE_DIR, 'result', '{0}.out'.format(SHOW_NAME)), 'w', encoding='utf8') as f:
json.dump(image_rec_res, f, ensure_ascii=False)
# plt.figure(SHOW_NAME)
# plt.imshow(image)
if IMAGE_SHOW:
cv2.imshow(SHOW_NAME, image)
else:
write_path = os.path.join(PATH_TO_IMAGE_DIR, 'result', SHOW_NAME)
print('valid write path: {0}'.format(write_path))
cv2.imwrite(write_path, image)
# Press any key to close the image
if IMAGE_SHOW:
while (1):
c = cv2.waitKey(0)
print('loop wait esc')
if c == 27:
print('will close!!!!')
cv2.destroyAllWindows()
break
# # Clean up
# cv2.destroyAllWindows()