Nvprof_Jetson_Nano_Example

使用TRTEXEC產生PROFILING結果

https://github.com/F64081169/Nvprof_Jetson_Nano_Example/tree/main/yolov4-tiny-profilingResult

• 產生資訊放於yolov4-tiny-profilingResult

新增cu_prof_start() and cu_prof_stop() in nvprof.py.

def loop_and_detect(cam, trt_yolo, conf_th, vis):
    """Continuously capture images from camera and do object detection.
    # Arguments
      cam: the camera instance (video source).
      trt_yolo: the TRT YOLO object detector instance.
      conf_th: confidence/score threshold for object detection.
      vis: for visualization.
    """
    full_scrn = False
    fps = 0.0
    tic = time.time()
    cu_prof_start() #for nvprof start profiling
    while True:
        if cv2.getWindowProperty(WINDOW_NAME, 0) < 0:
            break
        img = cam.read()
        if img is None:
            break
        boxes, confs, clss = trt_yolo.detect(img, conf_th)
        img = vis.draw_bboxes(img, boxes, confs, clss)
        img = show_fps(img, fps)
        cv2.imshow(WINDOW_NAME, img)
        toc = time.time()
        curr_fps = 1.0 / (toc - tic)
        # calculate an exponentially decaying average of fps number
        fps = curr_fps if fps == 0.0 else (fps*0.95 + curr_fps*0.05)
        tic = toc        
        key = cv2.waitKey(1)
        if key == 27:  # ESC key: quit program
            break
        elif key == ord('F') or key == ord('f'):  # Toggle fullscreen
            full_scrn = not full_scrn
            set_display(WINDOW_NAME, full_scrn)
        cu_prof_stop() #for nvprof stop profiling

start profiling function 加於while loop前

stop profiling function 加於while loop最後

• 即可觀察每次inference的執行資訊

results

reference

1. [腾讯机智] tensorflow profiling工具简介——nvprof和nvvp
2. Jetson上的零拷贝
3. NVVP Tutorial Gist
4. Cuda Toolkit Documentation