-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathpruebas.py
224 lines (184 loc) · 9.44 KB
/
pruebas.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
223
224
from pathlib import Path
import cv2
import time
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
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 = '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, class_id=None):
"""Feed forward an image into the object detection model.
Args:
image (ndarray): Input image in numpy format (OpenCV format).
sess: TF session.
graph: Object detection model loaded before.
class_id (list): Optional. Id's of the classes you want to detect.
Refer to mscoco_label_map.pbtxt' to find out more.
Returns:
output_dict (dict): Contains the info related to the detections.
"""
# 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)
if class_id is not None:
discrimine_class(class_id, output_dict)
return output_dict
def discrimine_class(class_id, output_dict):
"""Take just one class instances in the image of interest
Args:
class_id (int): Id's of the classes you want to detect. Refer to
mscoco_label_map.pbtxt' to find out more.
output_dict (dict): Output if the model once an image is processed.
Returns:
output_dict (dict): Modified dictionary wjich just delivers the
specified class detections.
"""
total_observations = 0 # Total observations per frame
for i in range(output_dict['detection_classes'].size):
if output_dict['detection_classes'][i] in class_id and output_dict['detection_scores'][i]>=0.5:
# The detection is from the desired category and with enough confidence
total_observations += 1
elif output_dict['detection_classes'][i] not in class_id:
# As this is a not desired detection, the score is artificially lowered
output_dict['detection_scores'][i] = 0.02
print("######################### " + str(total_observations) + " ########################")
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 detect_objects(image_np, sess, detection_graph):
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image_np, axis=0)
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
boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each mask represents a class instance detected in the frame
masks = detection_graph.get_tensor_by_name('detection_masks: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.
scores = detection_graph.get_tensor_by_name('detection_scores:0')
classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Actual detection
(boxes, masks, scores, classes, num_detections) = sess.run(
[boxes, masks, scores, classes, num_detections],
feed_dict={image_tensor: image_np_expanded})
# Print every class + probability prediction
classes_np = np.squeeze(classes).astype(np.int32)
#print(classes_np)
scores_np = np.squeeze(scores)
#print("Scores 1\n")
#print(scores_np)
# # Draw just class 1 detections (Person)
# total_people = 0 # Total observations per frame
# for i in range(classes_np.size):
# if classes_np[i]==1 and scores_np[i]>=0.5:
# total_people += 1
# elif classes_np[i] != 1:
# scores_np[i] = 0.02
# print("######################### " + str(total_people) + " ########################")
#print("Scores 2\n")
#print(scores_np)
# Visualization of the results of a detection
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
scores_np,
category_index,
instance_masks=np.squeeze(masks),
use_normalized_coordinates=True,
min_score_thresh=.5,
line_thickness=2)
return image_np
def main():
video_capture = cv2.VideoCapture(0)
detection_graph = model_load_into_memory()
try:
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
while True:
# Camera detection loop
_, frame = video_capture.read()
cv2.imshow('Entrada', frame)
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
t = time.time()
output = run_inference_for_single_image(frame, sess, detection_graph, [1, 44])
processed_image = visualize_results(frame, output)
cv2.imshow('Video', cv2.cvtColor(processed_image, cv2.COLOR_BGR2RGB))
#fps.update()
print('[INFO] elapsed time: {:.2f}'.format(time.time() - t))
if cv2.waitKey(1) & 0xFF == ord('q'):
break
except KeyboardInterrupt:
video_capture.release()
cv2.destroyAllWindows()
if __name__ == '__main__':
main()