object_detection_demo_ssd_async2.py

#!/usr/bin/env python
"""
 Copyright (c) 2018 Intel Corporation

 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.
 You may obtain a copy of the License at

      http://www.apache.org/licenses/LICENSE-2.0

 Unless required by applicable law or agreed to in writing, software
 distributed under the License is distributed on an "AS IS" BASIS,
 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
 limitations under the License.
"""

from __future__ import print_function
import sys
import os
from argparse import ArgumentParser
import cv2
import time
import logging as log
from openvino.inference_engine import IENetwork, IEPlugin
from timeit import default_timer as timer


def build_argparser():
    parser = ArgumentParser()
    parser.add_argument(
        "-m",
        "--model",
        help="Path to an .xml file with a trained model.",
        required=True,
        type=str)
    parser.add_argument(
        "-i",
        "--input",
        help="Path to video file or image. 'cam' for capturing video stream from camera",
        required=True,
        type=str)
    parser.add_argument(
        "-l",
        "--cpu_extension",
        help="MKLDNN (CPU)-targeted custom layers.Absolute path to a shared library with the kernels "
        "impl.",
        type=str,
        default=None)
    parser.add_argument(
        "-pp",
        "--plugin_dir",
        help="Path to a plugin folder",
        type=str,
        default=None)
    parser.add_argument(
        "-d",
        "--device",
        help="Specify the target device to infer on; CPU, GPU, FPGA or MYRIAD is acceptable. Demo "
        "will look for a suitable plugin for device specified (CPU by default)",
        default="CPU",
        type=str)
    parser.add_argument(
        "--labels", help="Labels mapping file", default=None, type=str)
    parser.add_argument(
        "-pt",
        "--prob_threshold",
        help="Probability threshold for detections filtering",
        default=0.5,
        type=float)

    return parser


def main():
    log.basicConfig(
        format="[ %(levelname)s ] %(message)s",
        level=log.INFO,
        stream=sys.stdout)
    args = build_argparser().parse_args()
    model_xml = args.model
    model_bin = os.path.splitext(model_xml)[0] + ".bin"
    # Plugin initialization for specified device and load extensions library if specified
    log.info("Initializing plugin for {} device...".format(args.device))
    plugin = IEPlugin(device=args.device, plugin_dirs=args.plugin_dir)
    if args.cpu_extension and 'CPU' in args.device:
        plugin.add_cpu_extension(args.cpu_extension)
    # Read IR
    log.info("Reading IR...")
    net = IENetwork(model=model_xml, weights=model_bin)

    if plugin.device == "CPU":
        supported_layers = plugin.get_supported_layers(net)
        not_supported_layers = [
            l for l in net.layers.keys() if l not in supported_layers
        ]
        if len(not_supported_layers) != 0:
            log.error(
                "Following layers are not supported by the plugin for specified device {}:\n {}".
                format(plugin.device, ', '.join(not_supported_layers)))
            log.error(
                "Please try to specify cpu extensions library path in demo's command line parameters using -l "
                "or --cpu_extension command line argument")
            sys.exit(1)
    assert len(
        net.inputs.keys()) == 1, "Demo supports only single input topologies"
    assert len(net.outputs) == 1, "Demo supports only single output topologies"
    input_blob = next(iter(net.inputs))
    out_blob = next(iter(net.outputs))
    log.info("Loading IR to the plugin...")
    exec_net = plugin.load(network=net, num_requests=2)
    # Read and pre-process input image
    n, c, h, w = net.inputs[input_blob].shape
    del net
    if args.input == 'cam':
        input_stream = 0
    else:
        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:
            labels_map = [x.strip() for x in f]
    else:
        labels_map = None

    #cap = cv2.imread(input_stream)
    cap = cv2.VideoCapture(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")
    is_async_mode = True
    render_time = 0
    ret, frame = cap.read()

    ##
    accum_time = 0
    curr_fps = 0
    fps = "FPS: ??"
    prev_time = timer()

    while cap.isOpened():
        if is_async_mode:
            ret, next_frame = cap.read()
        else:
            ret, frame = cap.read()
        if not ret:
            break
        initial_w = cap.get(3)
        initial_h = 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 is_async_mode:
            in_frame = cv2.resize(next_frame, (w, h))
            in_frame = in_frame.transpose(
                (2, 0, 1))  # Change data layout from HWC to CHW
            in_frame = in_frame.reshape((n, c, h, w))
            exec_net.start_async(
                request_id=next_request_id, inputs={input_blob: in_frame})
        else:
            in_frame = cv2.resize(frame, (w, h))
            in_frame = in_frame.transpose(
                (2, 0, 1))  # Change data layout from HWC to CHW
            in_frame = in_frame.reshape((n, c, h, w))
            if exec_net.requests[cur_request_id].wait(-1) == 0:
                exec_net.start_async(
                    request_id=cur_request_id, inputs={input_blob: in_frame})
        if 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 = exec_net.requests[cur_request_id].outputs[out_blob]
            for obj in res[0][0]:
                # Draw only objects when probability more than specified threshold
                if obj[2] > 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))
                    color = (0, 255, 0)
                    cv2.rectangle(frame, (xmin, ymin), (xmax, ymax), color, 2)
                    det_label = labels_map[class_id] if 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,
                        2)

            # Draw performance stats
            inf_time_message = "Inference time: N\A for async mode" if is_async_mode else \
                "Inference time: {:.3f} ms".format(det_time * 1000)
            render_time_message = "OpenCV rendering time: {:.3f} ms".format(
                render_time * 1000)
            async_mode_message = "Async mode is on. Processing request {}".format(cur_request_id) if is_async_mode else \
                "Async mode is off. Processing request {}".format(cur_request_id)

            ##
            frame = cv2.resize(frame, (w, h))
            cv2.putText(frame, inf_time_message, (15, 15),
                        cv2.FONT_HERSHEY_COMPLEX, 0.5, (200, 10, 10), 1)
            cv2.putText(frame, render_time_message, (15, 30),
                        cv2.FONT_HERSHEY_COMPLEX, 0.5, (10, 10, 200), 1)
            cv2.putText(frame, async_mode_message, (10, int(initial_h - 20)),
                        cv2.FONT_HERSHEY_COMPLEX, 0.5, (10, 10, 200), 1)

        ## ref. https://github.com/rykov8/ssd_keras/blob/master/testing_utils/videotest.py
        # Calculate FPS
        # This computes FPS for everything, not just the model's execution
        # which may or may not be what you want
        curr_time = timer()
        exec_time = curr_time - prev_time
        prev_time = curr_time
        accum_time = accum_time + exec_time
        curr_fps = curr_fps + 1
        if accum_time > 1:
            accum_time = accum_time - 1
            fps = "FPS: " + str(curr_fps)
            curr_fps = 0
        # Draw FPS in top left corner
        cv2.rectangle(frame, (w - 50, 0), (w, 17), (255, 255, 255), -1)
        cv2.putText(frame, fps, (w - 50 + 3, 10), cv2.FONT_HERSHEY_SIMPLEX,
                    0.35, (0, 0, 0), 1)

        #
        render_start = time.time()
        cv2.imshow("Detection Results", frame)
        render_end = time.time()
        render_time = render_end - render_start

        if is_async_mode:
            cur_request_id, next_request_id = next_request_id, cur_request_id
            frame = next_frame

        key = cv2.waitKey(1)
        if key == 27:
            break
        if (9 == key):
            is_async_mode = not is_async_mode
            log.info("Switched to {} mode".format("async" if is_async_mode else
                                                  "sync"))

    cv2.destroyAllWindows()
    del exec_net
    del plugin


if __name__ == '__main__':
    sys.exit(main() or 0)

Thank you, it is very useful. I tried this with multiprocessing calls. the key==27: break doesn't seem to close the windows. any idea on why and whats the intended purpose of it, if its not exiting and destroying all windows.