blob: cf8b4f79d5bdc707db0a06158db4a58a7d729171 [file] [log] [blame]
"""
SPDX-FileCopyrightText: 2020-present Open Networking Foundation <info@opennetworking.org>
SPDX-License-Identifier: LicenseRef-ONF-Member-1.01
"""
from __future__ import print_function
import cv2
import logging as log
import os
import sys
import time
from argparse import ArgumentParser, SUPPRESS
from imutils import build_montages
from openvino.inference_engine import IECore
from base_camera import BaseCamera
def build_argparser():
parser = ArgumentParser(add_help=False)
args = parser.add_argument_group('Options')
args.add_argument('-h', '--help', action='help', default=SUPPRESS, help='Show this help message and exit.')
args.add_argument("-m", "--model", help="Required. Path to an .xml file with a trained model.",
required=True, type=str)
args.add_argument("-i", "--input",
help="Required. Path to video file or image. 'cam' for capturing video stream from camera",
required=True, type=str)
args.add_argument("-l", "--cpu_extension",
help="Optional. Required for CPU custom layers. Absolute path to a shared library with the "
"kernels implementations.", type=str, default=None)
args.add_argument("-pp", "--plugin_dir", help="Optional. Path to a plugin folder", type=str, default=None)
args.add_argument("-d", "--device",
help="Optional. Specify the target device to infer on; CPU, GPU, FPGA, HDDL or MYRIAD is "
"acceptable. The demo will look for a suitable plugin for device specified. "
"Default value is CPU", default="CPU", type=str)
args.add_argument("--labels", help="Optional. Path to labels mapping file", default=None, type=str)
args.add_argument("-pt", "--prob_threshold", help="Optional. Probability threshold for detections filtering",
default=0.5, type=float)
args.add_argument("-ns", help='No show output', action='store_true')
return parser
class Camera(BaseCamera):
def __init__(self, device, args):
log.basicConfig(format="[ %(levelname)s ] %(message)s", level=log.INFO, stream=sys.stdout)
model_xml = args.model
model_bin = os.path.splitext(model_xml)[0] + ".bin"
# Read IR
log.info("Reading IR...")
net = IECore().read_network(model=model_xml, weights=model_bin)
assert len(net.inputs.keys()) == 1, "Demo supports only single input topologies"
assert len(net.outputs) == 1, "Demo supports only single output topologies"
self.input_blob = next(iter(net.inputs))
self.out_blob = next(iter(net.outputs))
log.info("Loading IR to the plugin...")
self.exec_net = IECore().load_network(network=net, device_name=args.device, num_requests=2)
# Read and pre-process input image
self.n, self.c, self.h, self.w = net.inputs[self.input_blob].shape
del net
if args.input == 'cam':
self.input_stream = 0
elif args.input == 'gstreamer':
# gst rtp sink
self.input_stream = 'udpsrc port=500' + device + ' caps = " application/x-rtp, encoding-name=JPEG,payload=26" ! rtpjpegdepay ! decodebin ! videoconvert ! appsink'
#input_stream = 'udpsrc port=5000 caps = "application/x-rtp, media=(string)video, clock-rate=(int)90000, encoding-name=(string)H264, payload=(int)96" ! rtph264depay ! decodebin ! videoconvert ! appsink'
print("input_stream:", self.input_stream)
else:
self.input_stream = args.input
assert os.path.isfile(args.input), "Specified input file doesn't exist"
if args.labels:
with open(args.labels, 'r') as f:
self.labels_map = [x.strip() for x in f]
else:
self.labels_map = None
self.args = args
super(Camera, self).__init__(device)
def __del__(self):
self.cap.release()
cv2.destroyAllWindows()
def frames(self):
if self.input_stream == 'gstreamer':
self.cap = cv2.VideoCapture(self.input_stream, cv2.CAP_GSTREAMER)
else:
self.cap = cv2.VideoCapture(self.input_stream)
cur_request_id = 0
next_request_id = 1
log.info("Starting inference in async mode...")
log.info("To switch between sync and async modes press Tab button")
log.info("To stop the demo execution press Esc button")
# Async doesn't work if True
# Request issues = Runtime Error: [REQUEST BUSY]
self.is_async_mode = False
#is_async_mode = True
render_time = 0
ret, frame = self.cap.read()
print("To close the application, press 'CTRL+C' or any key with focus on the output window")
while True:
if self.is_async_mode:
ret, next_frame = self.cap.read()
else:
ret, frame = self.cap.read()
if not ret:
break
initial_w = self.cap.get(3)
initial_h = self.cap.get(4)
# Main sync point:
# in the truly Async mode we start the NEXT infer request, while waiting for the CURRENT to complete
# in the regular mode we start the CURRENT request and immediately wait for it's completion
inf_start = time.time()
if self.is_async_mode:
in_frame = cv2.resize(next_frame, (self.w, self.h))
in_frame = in_frame.transpose((2, 0, 1)) # Change data layout from HWC to CHW
in_frame = in_frame.reshape((self.n, self.c, self.h, self.w))
self.exec_net.start_async(request_id=next_request_id, inputs={self.input_blob: in_frame})
else:
in_frame = cv2.resize(frame, (self.w, self.h))
in_frame = in_frame.transpose((2, 0, 1)) # Change data layout from HWC to CHW
in_frame = in_frame.reshape((self.n, self.c, self.h, self.w))
self.exec_net.start_async(request_id=cur_request_id, inputs={self.input_blob: in_frame})
if self.exec_net.requests[cur_request_id].wait(-1) == 0:
inf_end = time.time()
det_time = inf_end - inf_start
# Parse detection results of the current request
res = self.exec_net.requests[cur_request_id].outputs[self.out_blob]
for obj in res[0][0]:
# Draw only objects when probability more than specified threshold
if obj[2] > self.args.prob_threshold:
xmin = int(obj[3] * initial_w)
ymin = int(obj[4] * initial_h)
xmax = int(obj[5] * initial_w)
ymax = int(obj[6] * initial_h)
class_id = int(obj[1])
# Draw box and label\class_id
color = (min(class_id * 12.5, 255),min(class_id * 7, 255), min(class_id * 5, 255))
cv2.rectangle(frame, (xmin, ymin), (xmax, ymax), color, 2)
det_label = self.labels_map[class_id] if self.labels_map else str(class_id)
cv2.putText(frame, det_label + ' ' + str(round(obj[2] * 100, 1)) + ' %', (xmin, ymin - 7),
cv2.FONT_HERSHEY_COMPLEX, 0.6, color, 1)
# print('Object detected, class_id:', class_id, 'probability:', obj[2], 'xmin:', xmin, 'ymin:', ymin,
# 'xmax:', xmax, 'ymax:', ymax)
cv2.putText(frame, self.device, (10, int(initial_h - 20)),
cv2.FONT_HERSHEY_COMPLEX, 0.5, (10, 10, 200), 1)
render_start = time.time()
yield cv2.imencode('.jpg', frame)[1].tobytes()
render_end = time.time()
render_time = render_end - render_start
if self.is_async_mode:
cur_request_id, next_request_id = next_request_id, cur_request_id
frame = next_frame
if __name__ == '__main__':
args = build_argparser().parse_args()
camera = Camera(args)
camera.frames()
del camera