-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathinstance_segmentation.py
137 lines (112 loc) · 5.87 KB
/
instance_segmentation.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
import argparse
from pathlib import Path
import cv2
import numpy as np
import tensorflow as tf
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
from object_detection.utils import ops as utils_ops
# Argument parser
parser = argparse.ArgumentParser()
argparse.ArgumentParser().add_argument
parser.add_argument("-i", "--image", default='images/scotty.jpg', type=str,
help="Path to input image")
parser.add_argument("-m", "--model", default='mask_rcnn_inception_v2_coco_2018_01_28',
help="Optionale. TensorFlow model used to perform the instance segmentation")
args = vars(parser.parse_args())
# Global variables initialization
CWD_PATH = Path('.')
TF_MODELS_PATH = Path('../TensorFlow Object Detection Models/trained_models')
# Path to frozen detection graph. This is the actual model that is used for the object detection
MODEL_NAME = args['model'] #'mask_rcnn_inception_v2_coco_2018_01_28'
PATH_TO_CKPT = TF_MODELS_PATH / MODEL_NAME / 'frozen_inference_graph.pb'
# List of the strings that is used to add correct label for each box
PATH_TO_LABELS = CWD_PATH / 'object_detection' / 'data' / 'mscoco_label_map.pbtxt'
NUM_CLASSES = 90
# Loading label map
label_map = label_map_util.load_labelmap(str(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)
def model_load_into_memory():
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(str(PATH_TO_CKPT), 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
return detection_graph
def run_inference_for_single_image(image, sess, graph):
# Get handles to input and output tensors
ops = tf.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.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.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].astype(np.float32)
return output_dict
def visualize_results(image, output_dict):
"""Returns the resulting image after being passed to the model.
Args:
image (ndarray): Original image given to the model.
output_dict (dict): Dictionary with all the information provided by the model.
Returns:
image (ndarray): Visualization of the results form above.
"""
vis_util.visualize_boxes_and_labels_on_image_array(
image,
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=4)
return image
def main():
if Path(args['image']).exists() is not True:
print("Image file not found")
exit()
detection_graph = model_load_into_memory()
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
img = cv2.imread(args['image'])
image = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
output = run_inference_for_single_image(image, sess, detection_graph)
processed_image = visualize_results(image, output)
processed_image = cv2.cvtColor(processed_image, cv2.COLOR_RGB2BGR)
cv2.imshow('Original image', img)
cv2.imshow('Instance Segmented image', processed_image)
cv2.waitKey(1) & 0xFF
input("Image segmentation completed: press the 'Enter' button to exit")
cv2.destroyAllWindows()
if __name__ == '__main__':
main()