-
Notifications
You must be signed in to change notification settings - Fork 0
/
test.py
148 lines (129 loc) · 7.12 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
# from distutils.version import StrictVersion
import os, sys,tarfile, zipfile
import numpy as np
import tensorflow as tf
import six.moves.urllib as urllib
from PIL import Image
from io import StringIO
from matplotlib import pyplot as plt
from collections import defaultdict
from object_detection.utils import ops as utils_ops
# Paths settings
THE_PATH = os.getcwd()
sys.path.append(THE_PATH)
sys.path.append(THE_PATH+"/object_detection")
PATH_TO_FROZEN_GRAPH = "./model/frozen_inference_graph.pb"
PATH_TO_LABELS = "./model/mscoco_label_map.pbtxt"
PATH_TO_TEST_IMAGES_DIR = './test'
PATH_TO_CROP_IMAGES_DIR = './crop'
l=os.listdir(PATH_TO_TEST_IMAGES_DIR)
print(l)
li=[x.split('.')[0] for x in l]
str_list = list(filter(None, li))
TEST_IMAGE_NAMES = str_list
filetype = '.jpg'
TEST_IMAGE_PATHS = [''.join((PATH_TO_TEST_IMAGES_DIR, '/', x, filetype)) for x in TEST_IMAGE_NAMES]
# print("test image path = ", TEST_IMAGE_PATHS)
IMAGE_SIZE = (12, 8) # Size, in inches, of the output images.
NUM_CLASSES = 1
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
sys.path.append("..")
# MODEL_NAME = 'faster_rcnn_resnet101_pets'
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.compat.v1.GraphDef()
with tf.io.gfile.GFile(PATH_TO_FROZEN_GRAPH, '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)
#print(category_index)
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)
def run_inference_for_single_image(image, graph):
with graph.as_default():
with tf.compat.v1.Session() as sess:
# Get handles to input and output tensors
ops = tf.compat.v1.get_default_graph().get_operations()
all_tensor_names = {output.name for op in ops for output in op.outputs}
tensor_dict = {}
for key in ['num_detections', 'detection_boxes', 'detection_scores','detection_classes', 'detection_masks']:
tensor_name = key + ':0'
if tensor_name in all_tensor_names:
tensor_dict[key] = tf.compat.v1.get_default_graph().get_tensor_by_name(tensor_name)
if 'detection_masks' in tensor_dict:
# The following processing is only for single image
detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0])
detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0])
# Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32)
detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1])
detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1])
detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
detection_masks, detection_boxes, image.shape[0], image.shape[1])
detection_masks_reframed = tf.cast(
tf.greater(detection_masks_reframed, 0.5), tf.uint8)
# Follow the convention by adding back the batch dimension
tensor_dict['detection_masks'] = tf.expand_dims(detection_masks_reframed, 0)
image_tensor = tf.compat.v1.get_default_graph().get_tensor_by_name('image_tensor:0')
# Run inference
output_dict = sess.run(tensor_dict,feed_dict={image_tensor: np.expand_dims(image, 0)})
# all outputs are float32 numpy arrays, so convert types as appropriate
output_dict['num_detections'] = int(output_dict['num_detections'][0])
output_dict['detection_classes'] = output_dict[
'detection_classes'][0].astype(np.uint8)
output_dict['detection_boxes'] = output_dict['detection_boxes'][0]
output_dict['detection_scores'] = output_dict['detection_scores'][0]
if 'detection_masks' in output_dict:
output_dict['detection_masks'] = output_dict['detection_masks'][0]
return output_dict
for image_path, image_name in zip(TEST_IMAGE_PATHS, TEST_IMAGE_NAMES):
print(image_path)
image = Image.open(image_path)
im_width, im_height = image.size
# 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.
output_dict = run_inference_for_single_image(image_np, detection_graph)
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(image_np,output_dict['detection_boxes'],
output_dict['detection_classes'],
output_dict['detection_scores'],
category_index,
instance_masks=output_dict.get('detection_masks'),
use_normalized_coordinates=True,
line_thickness=2,
min_score_thresh = 0.01)
# print("detection_boxes:")
# print(output_dict['detection_boxes'])
# print(type(output_dict['detection_boxes']),len(output_dict['detection_boxes']))
# print('detection_classes')
# print(output_dict['detection_classes'])
# print(type(output_dict['detection_classes']),len(output_dict['detection_classes']))
# print('detection_scores')
# print(output_dict['detection_scores'], len(output_dict['detection_scores']))
plt.imsave(''.join((PATH_TO_CROP_IMAGES_DIR, '//',image_name,"_MARKED", filetype)), image_np)
plt.imshow(image_np)
try:
ymin = output_dict['detection_boxes'][0][0]
xmin = output_dict['detection_boxes'][0][1]
ymax = output_dict['detection_boxes'][0][2]
xmax = output_dict['detection_boxes'][0][3]
(xminn, xmaxx, yminn, ymaxx) = (int(xmin * im_width), int(xmax * im_width), int(ymin * im_height), int(ymax * im_height))
area = (xminn, yminn, xmaxx, ymaxx)
cropped_image = image.crop(area)
cropped_image.save(''.join((PATH_TO_CROP_IMAGES_DIR, '/',image_name,"_CROPPED", filetype)))
except Exception:
pass
print('\n**************** detecting_scores ****************\n')
print(output_dict['detection_scores'][1:10])
print("-"*80)
#plt.figure(figsize=IMAGE_SIZE)
# plt.imshow(image_np)