Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

viame_csv_to_coco_json pipeline fails #172

Open
ltetrel opened this issue Jan 18, 2024 · 0 comments
Open

viame_csv_to_coco_json pipeline fails #172

ltetrel opened this issue Jan 18, 2024 · 0 comments

Comments

@ltetrel
Copy link
Collaborator

ltetrel commented Jan 18, 2024

Hi,

We are trying to convert our annotation in viame_csv format to coco json.
For that there is an example here.

I created a file input_image_list.txt which contains path to the images relative to the annotation annotations.csv and I am using the following command:

(viame) ltetrel@boo:/opt/viame_0.20.3$ source setup_viame.sh && bin/kwiver runner examples/detection_file_conversions/pipelines/viame_csv_to_coco_json.pipe -s image_reader:video_filename=PATH/TO/input_image_list.txt -s detection_reader:detected_object_input=PATH/TO/annotations.csv

However it fails with the following:

INFO: Could not load default logger factory. Using built-in logger.
/opt/viame_0.20.3/lib/python3.6/site-packages/torch/cuda/__init__.py:80: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 804: forward compatibility was attempted on non supported HW (Triggered internally at  /viame/packages/pytorch/c10/cuda/CUDAFunctions.cpp:112.)
  return torch._C._cuda_getDeviceCount() > 0
No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda'
/opt/viame_0.20.3/lib/python3.6/site-packages/mmcv/__init__.py:21: UserWarning: On January 1, 2023, MMCV will release v2.0.0, in which it will remove components related to the training process and add a data transformation module. In addition, it will rename the package names mmcv to mmcv-lite and mmcv-full to mmcv. See https://github.com/open-mmlab/mmcv/blob/master/docs/en/compatibility.md for more details.
  'On January 1, 2023, MMCV will release v2.0.0, in which it will remove '
2024-01-18 14:49:00.251 INFO registration.cxx(141): Current search path: /opt/viame_0.20.3/lib64/viame/processes
2024-01-18 14:49:00.251 INFO registration.cxx(141): Current search path: /opt/viame_0.20.3/lib/viame/processes
2024-01-18 14:49:00.251 INFO registration.cxx(141): Current search path: /opt/viame_0.20.3/lib64/viame/modules
2024-01-18 14:49:00.251 INFO registration.cxx(141): Current search path: /opt/viame_0.20.3/lib/viame/modules
2024-01-18 14:49:00.251 INFO registration.cxx(141): Current search path: /opt/viame_0.20.3/lib64/kwiver/plugins/processes
2024-01-18 14:49:00.251 INFO registration.cxx(141): Current search path: /opt/viame_0.20.3/lib/kwiver/plugins/processes
2024-01-18 14:49:00.251 INFO registration.cxx(141): Current search path: /opt/viame_0.20.3/lib64/kwiver/plugins/modules
2024-01-18 14:49:00.251 INFO registration.cxx(141): Current search path: /opt/viame_0.20.3/lib/kwiver/plugins/modules
2024-01-18 14:49:00.251 INFO registration.cxx(141): Current search path: /opt/viame_0.20.3/lib64/kwiver/plugins/algorithms
2024-01-18 14:49:00.251 INFO registration.cxx(141): Current search path: /opt/viame_0.20.3/lib/kwiver/plugins/algorithms
2024-01-18 14:49:00.251 INFO registration.cxx(141): Current search path: /viame/build/install/lib/kwiver/plugins
2024-01-18 14:49:00.251 INFO registration.cxx(141): Current search path: /opt/viame_0.20.3/bin/../lib/kwiver/plugins
Caught unhandled kwiver::vital::vital_exception: Path does not exist: detections.csv, thrown from /viame/packages/kwiver/vital/algo/detected_object_set_input.cxx:55

Any thoughts on this ?

Thanks for the help,

@ltetrel ltetrel changed the title Attempting to convert annotation from viame _csv format to coco viame_csv_to_coco_json pipeline fails Jan 18, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant