| """ |
| 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': |
| # M-JPEG |
| # self.input_stream = 'udpsrc port=500' + device + ' caps = " application/x-rtp, encoding-name=JPEG,payload=26" ! rtpjpegdepay ! decodebin ! videoconvert ! appsink' |
| # H.264 |
| self.input_stream = 'udpsrc port=500' + device + ' caps = " application/x-rtp, media=(string)video, clock-rate=(int)90000, encoding-name=(string)H264, payload=(int)96" ! rtph264depay ! avdec_h264 ! 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 |