def main():
# parse arguments
args = cli()
# setup processor and visualizer
processor = Processor(model=args['model'])
visualizer = Visualizer()
# fetch input
print('image arg', args['image'])
img = cv2.imread('inputs/{}'.format(args['image']))
# inference
output = processor.detect(img)
img = cv2.resize(img, (640, 640))
# object visualization
object_grids = processor.extract_object_grids(output)
visualizer.draw_object_grid(img, object_grids, 0.1)
# class visualization
class_grids = processor.extract_class_grids(output)
visualizer.draw_class_grid(img, class_grids, 0.01)
# bounding box visualization
boxes = processor.extract_boxes(output)
visualizer.draw_boxes(img, boxes)
# final results
boxes, confs, classes = processor.post_process(output)
visualizer.draw_results(img, boxes, confs, classes)
def main():
# parse arguments
args = cli()
# setup processor and visualizer
processor = Processor(model=args['model'])
visualizer = Visualizer()
# fetch input
print('image arg', args['image'])
# img = cv2.imread('inputs/{}'.format(args['image']))
input_image_paths = []
folder_path = args['image']
if os.path.isdir(folder_path):
ls = os.listdir(folder_path)
for file_name in sorted(ls, key=lambda x: str(x.split('.jpg')[0])):
input_image_paths.append(os.path.join(folder_path, file_name))
for input_image_path in input_image_paths:
img = cv2.imread(input_image_path)
# inference
output = processor.detect(img)
# final results
boxes, confs, classes = processor.post_process(output, conf_thres=0.3, iou_thres=0.4, origin_w=img.shape[1], origin_h=img.shape[0])
visualizer.draw_results(img, boxes, confs, classes)
def main():
# parse arguments
args = cli()
# setup processor and visualizer
processor = Processor(model=args['model'])
visualizer = Visualizer()
# fetch input
print('image arg', args['image'])
#img = cv2.imread('inputs/{}'.format(args['image']))
img = cv2.imread("/home/jiqing/jq/bottle/33/3 (3).jpg")
cap = cv2.VideoCapture(0)
while 1:
ret, frame = cap.read()
#print(type(img))
# inference
#output = processor.detect(img)
#img = cv2.resize(img, (640, 640))
output = processor.detect(frame)
img = cv2.resize(frame, (640, 640))
# object visualization
object_grids = processor.extract_object_grids(output)
#visualizer.draw_object_grid(img, object_grids, 0.1)
# class visualization
class_grids = processor.extract_class_grids(output)
#visualizer.draw_class_grid(img, class_grids, 0.01)
# bounding box visualization
boxes = processor.extract_boxes(output)
#visualizer.draw_boxes(img, boxes)
# final results
boxes, confs, classes = processor.post_process(output)
#print(classes)
#label = f'{names[int(classes)]} {confs:.2f}'
visualizer.draw_results(img, boxes, confs, classes)
help='whether to archive picture and discovery in archve folder')
parser.add_argument('--device',
default='',
help='device id (i.e. 0 or 0,1) or cpu')
parser.add_argument('--fake',
default=False,
type=bool,
help='whether to simulate zone discovery')
parser.add_argument('--language',
default='eng',
type=str,
help='detection language')
opt = parser.parse_args()
processor = Processor(opt.weights,
opt.info_path,
opt.device,
fake_mode=opt.fake,
archive_mode=opt.archive)
while True:
with torch.no_grad():
processor.detect(opt.img_path)
# wait
time.sleep(5)
# delete old processed files
delete_old_files(opt.info_path)
def main():
# parse arguments
args = cli()
# setup processor and visualizer
processor = Processor(model=args['model'])
# visualizer = Visualizer()
catigories = [
"no_violence", # 0
"yes_violence" # 1
]
print("Open camera...")
# cap = cv2.VideoCapture(0)
# cap = cv2.VideoCapture('no1_xvid.avi')
# cap = cv2.VideoCapture('output.avi')
# cap = cv2.VideoCapture('fi1_xvid.avi')
cap = cv2.VideoCapture('yes_and_no.mp4')
# cap = cv2.VideoCapture('reallife.mp4')
print(cap)
# set a lower resolution for speed up
# cap.set(cv2.CAP_PROP_FRAME_WIDTH, 320)
# cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 240)
# env variables
full_screen = False
cv2.namedWindow(WINDOW_NAME, cv2.WINDOW_NORMAL)
cv2.resizeWindow(WINDOW_NAME, 640, 480)
cv2.moveWindow(WINDOW_NAME, 0, 0)
cv2.setWindowTitle(WINDOW_NAME, WINDOW_NAME)
t = None
index = 0
i_frame = -1
print("Ready!")
while True:
i_frame += 1
_, img = cap.read() # (480, 640, 3) 0 ~ 255
print(img.shape)
if i_frame % 2 == 0:
t1 = time.time()
idx = processor.detect(img)
print("cls:", catigories[idx])
t2 = time.time()
current_time = t2 - t1
print("current_time", current_time)
img = cv2.resize(img, (640, 480))
img = img[:, ::-1]
height, width, _ = img.shape
label = np.zeros([height // 10, width, 3]).astype('uint8') + 255
cv2.putText(label, 'Prediction: ' + catigories[idx],
(0, int(height / 16)), cv2.FONT_HERSHEY_SIMPLEX, 0.7,
(0, 0, 0), 2)
cv2.putText(label, '{:.1f} Vid/s'.format(1 / current_time),
(width - 170, int(height / 16)), cv2.FONT_HERSHEY_SIMPLEX,
0.7, (0, 0, 0), 2)
img = np.concatenate((img, label), axis=0)
cv2.imshow(WINDOW_NAME, img)
key = cv2.waitKey(1)
if key & 0xFF == ord('q') or key == 27: # exit
break
elif key == ord('F') or key == ord('f'): # full screen
print('Changing full screen option!')
full_screen = not full_screen
if full_screen:
print('Setting FS!!!')
cv2.setWindowProperty(WINDOW_NAME, cv2.WND_PROP_FULLSCREEN,
cv2.WINDOW_FULLSCREEN)
else:
cv2.setWindowProperty(WINDOW_NAME, cv2.WND_PROP_FULLSCREEN,
cv2.WINDOW_NORMAL)
# t5 = time.time()
# print("t5-t4:", t5 - t4)
if t is None:
t = time.time()
else:
nt = time.time()
index += 1
t = nt
cap.release()
cv2.destroyAllWindows()
