C++ API cost much more time compare to python API

[zoumengchao]

ret = rknn_outputs_get(ctx, 2, outputs, nullptr)
this API need too much time, the same rknn model ,Python need 9ms one imgs ,but C++ API need 20ms C++ API do not use NPU?

    double timeConsume,start;
    start = static_cast<double>(cv::getTickCount());    //记录当前时刻CPU时钟周期

    for (int j=0;j<300;j++){
        // Load image
        inputs[0].buf = img.data;
        ret = rknn_inputs_set(ctx, 1, inputs);
        if(ret < 0) {
            printf("rknn_input_set fail! ret=%d\n", ret);
            goto Error;
        }

        // Start Inference
        ret = rknn_run(ctx, nullptr);
        if(ret < 0) {
            printf("rknn_run fail! ret=%d\n", ret);
            goto Error;
        }
    
        outputs[0].want_float = true;
        outputs[0].is_prealloc = false;
        outputs[1].want_float = true;
        outputs[1].is_prealloc = false;
        ret = rknn_outputs_get(ctx, 2, outputs, nullptr);
        if(ret < 0) {
            printf("rknn_outputs_get fail! ret=%d\n", ret);
            goto Error;
        }
    }
    timeConsume = ((double)cv::getTickCount() - start) / cv::getTickFrequency();
    printf("\n timeSonsume: %f\n" ,timeConsume    );