Need some help running Demo examples

[imchwan]

Dear @Zhongdao , First of all, thank you for sharing this great work!

I'm just trying to run the demo examples from the script below with your pretrained weights. https://github.com/Zhongdao/Towards-Realtime-MOT#docker-demo-example

My running code: _python demo.py --input-video /mnt/choong/Database/infiniq2018_PeopleCounting/videos_selected/PC_088_CAM3_2/videos/PC_088_CAM3_260sec.mp4 --weights /mnt/choong/Towards-Realtime-MOT/weights/jde.1088x608.uncertainty.pt --output-format video --output-root /mnt/choong/Towards-Realtime-MOT/output

And I have below error messages... It looks like something is wrong with Numba..but I'm not quite sure what's the problem. Can you please point me out some clue? Thank you in advance.

----ERROR MESSAGE----- Namespace(cfg='cfg/yolov3_1088x608.cfg', conf_thres=0.5, input_video='/mnt/choong/Database/infiniq2018_PeopleCounting/videos_selected/PC_088_CAM3_2/videos/PC_088_CAM3_2_60sec.mp4', io u_thres=0.5, min_box_area=200, nms_thres=0.4, output_format='video', output_root='/mnt/choong/Towards-Realtime-MOT/output', track_buffer=30, weights='/mnt/choong/Towards-Realtime-MOT/ weights/jde.1088x608.uncertainty.pt')

2020-03-19 11:42:05 [INFO]: Starting tracking... Lenth of the video: 1799 frames Start eval_seq 2020-03-19 11:42:11 [INFO]: Processing frame 0 (100000.00 fps) /mnt/choong/Towards-Realtime-MOT/tracker/multitracker.py:140: NumbaWarning: Compilation is falling back to object mode WITH looplifting enabled because Function "tlbr_to_tlwh" failed type inference due to: non-precise type pyobject [1] During: typing of argument at /mnt/choong/Towards-Realtime-MOT/tracker/multitracker.py (143)

File "tracker/multitracker.py", line 143: def tlbr_to_tlwh(tlbr): ret = np.asarray(tlbr).copy() ^

@staticmethod /opt/conda/lib/python3.6/site-packages/numba/object_mode_passes.py:178: NumbaWarning: Function "tlbr_to_tlwh" was compiled in object mode without forceobj=True.

File "tracker/multitracker.py", line 142: @jit def tlbr_to_tlwh(tlbr): ^

state.func_ir.loc)) /opt/conda/lib/python3.6/site-packages/numba/object_mode_passes.py:188: NumbaDeprecationWarning: Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit http://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "tracker/multitracker.py", line 142: @jit def tlbr_to_tlwh(tlbr): ^

state.func_ir.loc)) /mnt/choong/Towards-Realtime-MOT/tracker/multitracker.py:116: NumbaWarning: Compilation is falling back to object mode WITH looplifting enabled because Function "tlbr" failed type inference due to: non-precise type pyobject [1] During: typing of argument at /mnt/choong/Towards-Realtime-MOT/tracker/multitracker.py (122)

File "tracker/multitracker.py", line 122: def tlbr(self):

    """
    ret = self.tlwh.copy()
    ^

@property /opt/conda/lib/python3.6/site-packages/numba/object_mode_passes.py:178: NumbaWarning: Function "tlbr" was compiled in object mode without forceobj=True.

File "tracker/multitracker.py", line 118: @jit def tlbr(self): ^

state.func_ir.loc)) /opt/conda/lib/python3.6/site-packages/numba/object_mode_passes.py:188: NumbaDeprecationWarning: Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit http://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "tracker/multitracker.py", line 118: @jit def tlbr(self): ^

state.func_ir.loc)) /mnt/choong/Towards-Realtime-MOT/tracker/multitracker.py:103: NumbaWarning: Compilation is falling back to object mode WITH looplifting enabled because Function "tlwh" failed type inference due to: non-precise type pyobject [1] During: typing of argument at /mnt/choong/Towards-Realtime-MOT/tracker/multitracker.py (109)

File "tracker/multitracker.py", line 109: def tlwh(self):

    """
    if self.mean is None:
    ^

@property /opt/conda/lib/python3.6/site-packages/numba/object_mode_passes.py:178: NumbaWarning: Function "tlwh" was compiled in object mode without forceobj=True.

File "tracker/multitracker.py", line 105: @jit def tlwh(self): ^

state.func_ir.loc)) /opt/conda/lib/python3.6/site-packages/numba/object_mode_passes.py:188: NumbaDeprecationWarning: Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit http://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "tracker/multitracker.py", line 105: @jit def tlwh(self): ^

state.func_ir.loc)) 2020-03-19 11:42:12 [INFO]: name 'logger' is not defined

[Zhongdao]

2020-03-19 11:42:12 [INFO]: name 'logger' is not defined It seems the logger is not properly initialized?

[imchwan]

Thank you for the comments. I just added

from utils.log import logger at multitracker.py, and that error was not seen.

And also I commented out jit at multitracker.py related to the Numba(using @jit...).

Still modifying codes a little to remove errors in the code, however, I think I'm doing something wrong... But the problem is...I'm not sure what's the problem. (It seems like it's only me that cannot run the demo ;( )

Can I check one more thing? Below script is the only thing I need to do before running python demo.py, right? I just want to know what am I missing... I have tried this in 2 different machines, but still have some problems.

docker build -t towards-realtime-mot docker/
docker run --rm --gpus all -v $(pwd)/:/Towards-Realtime-MOT -ti towards-realtime-mot /bin/bash

Thank you in advace!

[woailuoshenqi]

I have this problem, too. Have you solved?

[imchwan]

@woailuoshenqi I have pulled latest version which was updated by denverdash:bugfix (Bugfix #122). Then the problem was solved. =)

[woailuoshenqi]

Thanks!

@woailuoshenqi I have pulled latest version which was updated by denverdash:bugfix (Bugfix #122). Then the problem was solved. =) Thanks！