-
Notifications
You must be signed in to change notification settings - Fork 103
/
yolo.py
147 lines (110 loc) · 3.96 KB
/
yolo.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
import cv2
import time
import sys
import numpy as np
def build_model(is_cuda):
net = cv2.dnn.readNet("config_files/yolov5s.onnx")
if is_cuda:
print("Attempty to use CUDA")
net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA)
net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA_FP16)
else:
print("Running on CPU")
net.setPreferableBackend(cv2.dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
return net
INPUT_WIDTH = 640
INPUT_HEIGHT = 640
SCORE_THRESHOLD = 0.2
NMS_THRESHOLD = 0.4
CONFIDENCE_THRESHOLD = 0.4
def detect(image, net):
blob = cv2.dnn.blobFromImage(image, 1/255.0, (INPUT_WIDTH, INPUT_HEIGHT), swapRB=True, crop=False)
net.setInput(blob)
preds = net.forward()
return preds
def load_capture():
capture = cv2.VideoCapture("sample.mp4")
return capture
def load_classes():
class_list = []
with open("config_files/classes.txt", "r") as f:
class_list = [cname.strip() for cname in f.readlines()]
return class_list
class_list = load_classes()
def wrap_detection(input_image, output_data):
class_ids = []
confidences = []
boxes = []
rows = output_data.shape[0]
image_width, image_height, _ = input_image.shape
x_factor = image_width / INPUT_WIDTH
y_factor = image_height / INPUT_HEIGHT
for r in range(rows):
row = output_data[r]
confidence = row[4]
if confidence >= 0.4:
classes_scores = row[5:]
_, _, _, max_indx = cv2.minMaxLoc(classes_scores)
class_id = max_indx[1]
if (classes_scores[class_id] > .25):
confidences.append(confidence)
class_ids.append(class_id)
x, y, w, h = row[0].item(), row[1].item(), row[2].item(), row[3].item()
left = int((x - 0.5 * w) * x_factor)
top = int((y - 0.5 * h) * y_factor)
width = int(w * x_factor)
height = int(h * y_factor)
box = np.array([left, top, width, height])
boxes.append(box)
indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.25, 0.45)
result_class_ids = []
result_confidences = []
result_boxes = []
for i in indexes:
result_confidences.append(confidences[i])
result_class_ids.append(class_ids[i])
result_boxes.append(boxes[i])
return result_class_ids, result_confidences, result_boxes
def format_yolov5(frame):
row, col, _ = frame.shape
_max = max(col, row)
result = np.zeros((_max, _max, 3), np.uint8)
result[0:row, 0:col] = frame
return result
colors = [(255, 255, 0), (0, 255, 0), (0, 255, 255), (255, 0, 0)]
is_cuda = len(sys.argv) > 1 and sys.argv[1] == "cuda"
net = build_model(is_cuda)
capture = load_capture()
start = time.time_ns()
frame_count = 0
total_frames = 0
fps = -1
while True:
_, frame = capture.read()
if frame is None:
print("End of stream")
break
inputImage = format_yolov5(frame)
outs = detect(inputImage, net)
class_ids, confidences, boxes = wrap_detection(inputImage, outs[0])
frame_count += 1
total_frames += 1
for (classid, confidence, box) in zip(class_ids, confidences, boxes):
color = colors[int(classid) % len(colors)]
cv2.rectangle(frame, box, color, 2)
cv2.rectangle(frame, (box[0], box[1] - 20), (box[0] + box[2], box[1]), color, -1)
cv2.putText(frame, class_list[classid], (box[0], box[1] - 10), cv2.FONT_HERSHEY_SIMPLEX, .5, (0,0,0))
if frame_count >= 30:
end = time.time_ns()
fps = 1000000000 * frame_count / (end - start)
frame_count = 0
start = time.time_ns()
if fps > 0:
fps_label = "FPS: %.2f" % fps
cv2.putText(frame, fps_label, (10, 25), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
cv2.imshow("output", frame)
if cv2.waitKey(1) > -1:
print("finished by user")
break
print("Total frames: " + str(total_frames))