FPS problem

[pangr]

when I test the code in P4 GPU， I found the FPS is lower than PySOT Model Zoo （r50 only have 20 fps）.Is anyone have same problem?

[ZhiyuanChen]

I couldn't understand your problem
What do you mean by PySot model zoo?

[vhnamgau]

In your document: FPS ~ 80 FPS
I have the same problem with GTX 2080Ti -> 15.37 frame per second.

In tools/demo.py, we add count and start_time variable to calculate FPS
# build tracker
tracker = build_tracker(model)

first_frame = True
if args.video_name:
    video_name = args.video_name.split('/')[-1].split('.')[0]
else:
    video_name = 'webcam'
cv2.namedWindow(video_name, cv2.WND_PROP_FULLSCREEN)
start_time = time.time()
count = 0
for frame in get_frames(args.video_name):
    count += 1
    if first_frame:
        try:
            init_rect = cv2.selectROI(video_name, frame, False, False)
        except:
            exit()
        tracker.init(frame, init_rect)
        first_frame = False
    else:
        outputs = tracker.track(frame)
        if 'polygon' in outputs:
            polygon = np.array(outputs['polygon']).astype(np.int32)
            cv2.polylines(frame, [polygon.reshape((-1, 1, 2))],
                          True, (0, 255, 0), 3)
            mask = ((outputs['mask'] > cfg.TRACK.MASK_THERSHOLD) * 255)
            mask = mask.astype(np.uint8)
            mask = np.stack([mask, mask*255, mask]).transpose(1, 2, 0)
            frame = cv2.addWeighted(frame, 0.77, mask, 0.23, -1)
        else:
            bbox = list(map(int, outputs['bbox']))
            cv2.rectangle(frame, (bbox[0], bbox[1]),
                          (bbox[0]+bbox[2], bbox[1]+bbox[3]),
                          (0, 255, 0), 3)
        #cv2.imshow(video_name, frame)
        #cv2.waitKey(40)

print(count / (time.time() - start_time))

[buaacarzp]

您好，这个FPS是不是跟图像的大小有关系？ 我看官方好像没有如何去测试FPS的代码，vot中的图像的尺寸是一样大的吗？

[ZhiyuanChen]

In your document: FPS ~ 80 FPS
I have the same problem with GTX 2080Ti -> 15.37 frame per second.

In tools/demo.py, we add count and start_time variable to calculate FPS

build tracker

tracker = build_tracker(model)

first_frame = True
if args.video_name:
    video_name = args.video_name.split('/')[-1].split('.')[0]
else:
    video_name = 'webcam'
cv2.namedWindow(video_name, cv2.WND_PROP_FULLSCREEN)
start_time = time.time()
count = 0
for frame in get_frames(args.video_name):
    count += 1
    if first_frame:
        try:
            init_rect = cv2.selectROI(video_name, frame, False, False)
        except:
            exit()
        tracker.init(frame, init_rect)
        first_frame = False
    else:
        outputs = tracker.track(frame)
        if 'polygon' in outputs:
            polygon = np.array(outputs['polygon']).astype(np.int32)
            cv2.polylines(frame, [polygon.reshape((-1, 1, 2))],
                          True, (0, 255, 0), 3)
            mask = ((outputs['mask'] > cfg.TRACK.MASK_THERSHOLD) * 255)
            mask = mask.astype(np.uint8)
            mask = np.stack([mask, mask*255, mask]).transpose(1, 2, 0)
            frame = cv2.addWeighted(frame, 0.77, mask, 0.23, -1)
        else:
            bbox = list(map(int, outputs['bbox']))
            cv2.rectangle(frame, (bbox[0], bbox[1]),
                          (bbox[0]+bbox[2], bbox[1]+bbox[3]),
                          (0, 255, 0), 3)
        #cv2.imshow(video_name, frame)
        #cv2.waitKey(40)

print(count / (time.time() - start_time))

Can you share the video?
What is your CUDA, CuDNN and PyTorch version?

[ZhiyuanChen]

Since no futrher question is asked, I'm closing this issue for now.
Please create a new issue should you have other questions.