-
Notifications
You must be signed in to change notification settings - Fork 0
/
object_detection.py
222 lines (162 loc) · 7.4 KB
/
object_detection.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
216
217
218
219
220
221
222
# coding: utf-8
print('ok')
# # Object Detection Demo
# Welcome to the object detection inference walkthrough! This notebook will walk you step by step through the process of using a pre-trained model to detect objects in an image. Make sure to follow the [installation instructions](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md) before you start.
# # Imports
# In[ ]:
import numpy as np
import os
#import six.moves.urllib as urllib
import sys
#import tarfile
import tensorflow as tf
#import zipfile
#from collections import defaultdict
#from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
#if tf.__version__ != '1.4.0':
# raise ImportError('Please upgrade your tensorflow installation to v1.4.0!')
# ## Env setup
# In[ ]:
# This is needed to display the images.
get_ipython().magic('matplotlib inline')
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
# ## Object detection imports
# Here are the imports from the object detection module.
# In[ ]:
from utils import label_map_util
from utils import visualization_utils as vis_util
# # Model preparation
# ## Variables
#
# Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_CKPT` to point to a new .pb file.
#
# By default we use an "SSD with Mobilenet" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies.
# In[ ]:
# What model to download.
MODEL_NAME = 'numplate'
#MODEL_FILE = MODEL_NAME + '.tar.gz'
#DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'
# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/graph-200000/frozen_inference_graph.pb'
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('training', 'object-detection.pbtxt')
NUM_CLASSES = 1
# ## Download Model
# In[ ]:
# opener = urllib.request.URLopener()
# opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
# tar_file = tarfile.open(MODEL_FILE)
# for file in tar_file.getmembers():
# file_name = os.path.basename(file.name)
# if 'frozen_inference_graph.pb' in file_name:
# tar_file.extract(file, os.getcwd())
# ## Load a (frozen) Tensorflow model into memory.
# In[ ]:
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='')
# ## Loading label map
# Label maps map indices to category names, so that when our convolution network predicts `5`, we know that this corresponds to `airplane`. Here we use internal utility functions, but anything that returns a dictionary mapping integers to appropriate string labels would be fine
# In[ ]:
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)
# ## Helper code
# In[ ]:
def load_image_into_numpy_array(image):
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape(
(im_height, im_width, 3)).astype(np.uint8)
# # Detection
# In[ ]:
# For the sake of simplicity we will use only 2 images:
# image1.jpg
# image2.jpg
# If you want to test the code with your images, just add path to the images to the TEST_IMAGE_PATHS.
PATH_TO_TEST_IMAGES_DIR = 'test_images'
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.jpg'.format(i)) for i in range(1, 2) ]
# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)
TEST_DHARUN=os.path.join('numplate')
# In[ ]:
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')
for image_path in TEST_IMAGE_PATHS:
image = Image.open(image_path)
# the array based representation of the image will be used later in order to prepare the
# result image with boxes and labels on it.
image_np = load_image_into_numpy_array(image)
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image_np, axis=0)
# Actual detection.
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: image_np_expanded})
# Visualization of the results of a detection
# tf.image.draw_bounding_boxes(image_np, boxes, name=None)
# print(np.squeeze(boxes))
# print(category_index)
# print(boxes.shape[0])
# print(100*scores[0])
# ase=tf.constant(detection_scores,tf.float32)
# print(sess.run(ase))
# vis_util.encode_image_array_as_png_str(image_np)
# vis_util.save_image_array_as_png(image_np,TEST_DHARUN)
# width, height = image.size
# print(height)
# ymin = boxes[0][i][0]*height
# xmin = boxes[0][i][1]*width
# ymax = boxes[0][i][2]*height
# xmax = boxes[0][i][3]*width
# print(ymin)
# image=tf.image.convert_image_dtype(image,dtype=float,saturate=False,name=None)
class_fetch = int(classes[0,0])
ymin = boxes[0,0,0]
xmin = boxes[0,0,1]
ymax = boxes[0,0,2]
xmax = boxes[0,0,3]
(im_width, im_height) = image.size
(xminn, xmaxx, yminn, ymaxx) = (xmin * im_width, xmax * im_width, ymin * im_height, ymax * im_height)
print(ymin,xmin,ymax,xmax)
xxminn=int(xminn)
xxmaxx=int(xmaxx)
yyminn=int(yminn)
yymaxx=int(ymaxx)
# print(xxminn,xxmaxx,yyminn,yymaxx)
# cropped_image = tf.image.crop_to_bounding_box(image_np, int(yminn), int(xminn),int(ymaxx - yminn), int(xmaxx - xminn))
cropped_image = tf.image.crop_to_bounding_box(image, yyminn, xxminn, yymaxx - yyminn, xxmaxx - xxminn)
# output_image = tf.image.encode_png(cropped_image)
# sess = tf.Session()
img_data = sess.run(cropped_image)
# sess.close()
class_name = category_index[class_fetch]['name']
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=5)
print(class_name)
plt.figure(figsize=IMAGE_SIZE)
plt.imshow(image_np)
# plt.imshow(img_data)
# plt.imshow(output_image)
# plt.show()