forked from jkjung-avt/tensorrt_demos
-
Notifications
You must be signed in to change notification settings - Fork 0
/
trt_ssd.py
101 lines (82 loc) · 2.94 KB
/
trt_ssd.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
"""trt_ssd.py
This script demonstrates how to do real-time object detection with
TensorRT optimized Single-Shot Multibox Detector (SSD) engine.
"""
import sys
import time
import argparse
import cv2
import pycuda.autoinit # This is needed for initializing CUDA driver
from utils.ssd_classes import get_cls_dict
from utils.ssd import TrtSSD
from utils.camera import add_camera_args, Camera
from utils.display import open_window, set_display, show_fps
from utils.visualization import BBoxVisualization
WINDOW_NAME = 'TrtSsdDemo'
INPUT_HW = (300, 300)
SUPPORTED_MODELS = [
'ssd_mobilenet_v1_coco',
'ssd_mobilenet_v1_egohands',
'ssd_mobilenet_v2_coco',
'ssd_mobilenet_v2_egohands',
]
def parse_args():
"""Parse input arguments."""
desc = ('Capture and display live camera video, while doing '
'real-time object detection with TensorRT optimized '
'SSD model on Jetson Nano')
parser = argparse.ArgumentParser(description=desc)
parser = add_camera_args(parser)
parser.add_argument('--model', type=str, default='ssd_mobilenet_v2_coco',
choices=SUPPORTED_MODELS)
args = parser.parse_args()
return args
def loop_and_detect(cam, trt_ssd, conf_th, vis):
"""Continuously capture images from camera and do object detection.
# Arguments
cam: the camera instance (video source).
trt_ssd: the TRT SSD object detector instance.
conf_th: confidence/score threshold for object detection.
vis: for visualization.
"""
full_scrn = False
fps = 0.0
tic = time.time()
while True:
if cv2.getWindowProperty(WINDOW_NAME, 0) < 0:
break
img = cam.read()
if img is not None:
boxes, confs, clss = trt_ssd.detect(img, conf_th)
img = vis.draw_bboxes(img, boxes, confs, clss)
img = show_fps(img, fps)
cv2.imshow(WINDOW_NAME, img)
toc = time.time()
curr_fps = 1.0 / (toc - tic)
# calculate an exponentially decaying average of fps number
fps = curr_fps if fps == 0.0 else (fps*0.95 + curr_fps*0.05)
tic = toc
key = cv2.waitKey(1)
if key == 27: # ESC key: quit program
break
elif key == ord('F') or key == ord('f'): # Toggle fullscreen
full_scrn = not full_scrn
set_display(WINDOW_NAME, full_scrn)
def main():
args = parse_args()
cam = Camera(args)
cam.open()
if not cam.is_opened:
sys.exit('Failed to open camera!')
cls_dict = get_cls_dict(args.model.split('_')[-1])
trt_ssd = TrtSSD(args.model, INPUT_HW)
cam.start()
open_window(WINDOW_NAME, args.image_width, args.image_height,
'Camera TensorRT SSD Demo for Jetson Nano')
vis = BBoxVisualization(cls_dict)
loop_and_detect(cam, trt_ssd, conf_th=0.3, vis=vis)
cam.stop()
cam.release()
cv2.destroyAllWindows()
if __name__ == '__main__':
main()