系列 | OpenVINO使用之行人属性识别

模型名称:
pedestrian-detection-adas-0002
输入格式：NCHW= [1x3x384x672]
输出格式：DetectionOut 类型 [1, 1, N, 7] 

模型名称:
person-attributes-recognition-crossroad-0230
输入格式：NCHW=  [1x3x160x80]
输出格式：
输出层有三个，其中输出层名称为435的输出格式为
[1, 8, 1, 1] 是八个属性
另外两个输出层456，459表示两个颜色位置

# 加载MKLDNN - CPU Target
log.basicConfig(format="[ %(levelname)s ] %(message)s", level=log.INFO, stream=sys.stdout)
plugin = IEPlugin(device="CPU", plugin_dirs=plugin_dir)
plugin.add_cpu_extension(cpu_extension)

lut = [];
lut.append((0, 0, 255))
lut.append((255, 0, 0))
lut.append((0, 255, 0))
lut.append((0, 255, 255))
lut.append((255, 0, 255))
# 加载IR
log.info("Reading IR...")
net = IENetwork(model=model_xml, weights=model_bin)
pedestrian_attr_net = IENetwork(model=attribute_xml, weights=attribute_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"

# 获取输入输出层
input_blob = next(iter(net.inputs))
out_blob = next(iter(net.outputs))

lm_input_blob = next(iter(pedestrian_attr_net.inputs))
lm_output_blob = next(iter(pedestrian_attr_net.outputs))
log.info("Loading IR to the plugin...")

# 创建可执行网络
exec_net = plugin.load(network=net, num_requests=2)
lm_exec_net = plugin.load(network=pedestrian_attr_net)
n, c, h, w = net.inputs[input_blob].shape
del net

# we did not need pedestrian model any more
mn, mc, mh, mw = pedestrian_attr_net.inputs[lm_input_blob].shape
del pedestrian_attr_net

# 开始检测
while cap.isOpened():
    if is_async_mode:
        ret, next_frame = cap.read()
    else:
        ret, frame = cap.read()
    if not ret:
        break

    # next_frame = cv2.flip(next_frame, 1)

    # 开启同步或者异步执行模式
    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))
        exec_net.start_async(request_id=cur_request_id, inputs={input_blob: in_frame})
    if exec_net.requests[cur_request_id].wait(-1) == 0:

        # 解析DetectionOut
        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] > 0.5:
                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
                cv2.rectangle(frame, (xmin, ymin), (xmax, ymax), (0, 0, 255), 2)
                if xmin > 0 and ymin > 0 and (xmax < initial_w) and (ymax < initial_h):
                    roi = frame[ymin:ymax, xmin:xmax, :]
                    pedestrian_roi = cv2.resize(roi, (mw, mh))
                    pedestrian_roi = pedestrian_roi.transpose((2, 0, 1))
                    pedestrian_roi = pedestrian_roi.reshape((mn, mc, mh, mw))

                    # 行人属性识别
                    lm_exec_net.infer(inputs={'0': pedestrian_roi})
                    attr_res = lm_exec_net.requests[0].outputs[lm_output_blob]
                    attr_res = np.reshape(attr_res, (8, 1))

                    # 解析行人八个属性指标
                    for i in range(len(attrs)):
                        if attr_res[i][0] > 0.5:
                            cv2.putText(frame, attrs[i] + ": " + str(1),
                                        (xmin+30, ymin+20*i),
                                        cv2.FONT_HERSHEY_COMPLEX, 0.5, (0, 0, 255), 1)
                        else:
                            cv2.putText(frame, attrs[i] + ": " + str(0),
                                        (xmin + 30, ymin + 20 * i),
                                        cv2.FONT_HERSHEY_COMPLEX, 0.5, (0, 0, 255), 1)
                    cv2.putText(frame, "Person" + ' ' + str(round(obj[2] * 100, 1)) + ' %', (xmin, ymin - 7),
                                cv2.FONT_HERSHEY_COMPLEX, 0.5, (255, 0, 0), 1)
                    cv2.imwrite("D:/reslut.png", frame)
        inf_end = time.time()
        det_time = inf_end - inf_start

        # 显示绘制文本
        inf_time_message = "Inference time: {:.3f} ms， FPS:{:.3f}".format(det_time * 1000, 1000 / (det_time * 1000 + 1))
        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)

        cv2.putText(frame, inf_time_message, (15, 15), cv2.FONT_HERSHEY_COMPLEX, 0.5, (255, 255, 0), 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)

    # 显示
    render_start = time.time()
    cv2.imshow("OpenVINO-face-landmark-detection@57558865", frame)
    render_end = time.time()
    render_time = render_end - render_start

    # ready for next frame
    if is_async_mode:
        cur_request_id, next_request_id = next_request_id, cur_request_id
        frame = next_frame

    key = cv2.waitKey(50)
    if key == 27:
        break