Open briansodenkin opened 2 years ago
Here are the track record of the running of demo.my ! python demo.py --input-video ped_track.mp4 --weights models/jde.1088x608.uncertainty.pth \ --output-format video --output-root outputs/jde_1088X608_video Namespace(cfg='cfg/yolov3_1088x608.cfg', conf_thres=0.5, input_video='ped_track.mp4', iou_thres=0.5, min_box_area=200, nms_thres=0.4, output_format='video', output_root='outputs/jde_1088X608_video', track_buffer=30, weights='models/jde.1088x608.uncertainty.pth')
2021-12-19 11:50:43 [INFO]: Starting tracking... Lenth of the video: 900 frames 2021-12-19 11:50:55 [INFO]: Processing frame 0 (100000.00 fps) /usr/local/lib/python3.7/dist-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] 2021-12-19 11:50:57 [INFO]: Processing frame 20 (15.19 fps) 2021-12-19 11:50:58 [INFO]: Processing frame 40 (17.78 fps) 2021-12-19 11:51:00 [INFO]: Processing frame 60 (18.85 fps) 2021-12-19 11:51:01 [INFO]: Processing frame 80 (19.43 fps) 2021-12-19 11:51:02 [INFO]: Processing frame 100 (19.80 fps) 2021-12-19 11:51:04 [INFO]: Processing frame 120 (20.02 fps) 2021-12-19 11:51:05 [INFO]: Processing frame 140 (20.21 fps) 2021-12-19 11:51:06 [INFO]: Processing frame 160 (20.36 fps) 2021-12-19 11:51:08 [INFO]: Processing frame 180 (20.45 fps) 2021-12-19 11:51:09 [INFO]: Processing frame 200 (20.54 fps) 2021-12-19 11:51:10 [INFO]: Processing frame 220 (20.61 fps) 2021-12-19 11:51:12 [INFO]: Processing frame 240 (20.67 fps) 2021-12-19 11:51:13 [INFO]: Processing frame 260 (20.70 fps) /content/Towards-Realtime-MOT/tracker/multitracker.py:142: 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 During: typing of argument at /content/Towards-Realtime-MOT/tracker/multitracker.py (145)
File "tracker/multitracker.py", line 145: def tlbr_to_tlwh(tlbr): ret = np.asarray(tlbr).copy() ^
@staticmethod /usr/local/lib/python3.7/dist-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "tlbr_to_tlwh" was compiled in object mode without forceobj=True.
File "tracker/multitracker.py", line 144: @jit def tlbr_to_tlwh(tlbr): ^
state.func_ir.loc)) /usr/local/lib/python3.7/dist-packages/numba/core/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 https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit
File "tracker/multitracker.py", line 144: @jit def tlbr_to_tlwh(tlbr): ^
state.func_ir.loc)) /content/Towards-Realtime-MOT/tracker/multitracker.py:118: NumbaWarning: Compilation is falling back to object mode WITH looplifting enabled because Function "tlbr" failed type inference due to: non-precise type pyobject During: typing of argument at /content/Towards-Realtime-MOT/tracker/multitracker.py (124)
File "tracker/multitracker.py", line 124: def tlbr(self):
Hi, The log looks okay, could you try another mp4 player?
PotPlayer is good!
I have run the demo.py successfully on colab. However, the result.mp4 cannot be played. Is there method to resolve this ? Thank you