Error with Compreface component defined

[gofaster]

Hello, I'm testing Viseron 2.0b3 on a Jetson Nano with Jetpack 4.6. Decided to try enabling Compreface face recognition. During Viserson start, this error snippet is displayed

Traceback (most recent call last):
  File "/usr/local/lib/python3.8/threading.py", line 932, in _bootstrap_inner
    self.run()
  File "/usr/local/lib/python3.8/threading.py", line 870, in run
    self._target(*self._args, **self._kwargs)
  File "/src/viseron/components/__init__.py", line 470, in setup_component
    if component.setup_component(tries=tries):
  File "/src/viseron/components/__init__.py", line 122, in setup_component
    component_module = self.get_component()
  File "/src/viseron/components/__init__.py", line 88, in get_component
    return importlib.import_module(self._path)
  File "/usr/local/lib/python3.8/importlib/__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1014, in _gcd_import
  File "<frozen importlib._bootstrap>", line 991, in _find_and_load
  File "<frozen importlib._bootstrap>", line 975, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 671, in _load_unlocked
  File "<frozen importlib._bootstrap_external>", line 783, in exec_module
  File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
  File "/src/viseron/components/compreface/__init__.py", line 7, in <module>
    from viseron.components.compreface.face_recognition import ComprefaceTrain
  File "/src/viseron/components/compreface/face_recognition.py", line 12, in <module>
    from face_recognition.face_recognition_cli import image_files_in_folder
  File "/usr/local/lib/python3.8/site-packages/face_recognition/__init__.py", line 7, in <module>
    from .api import load_image_file, face_locations, batch_face_locations, face_landmarks, face_encodings, compare_faces, face_distance
  File "/usr/local/lib/python3.8/site-packages/face_recognition/api.py", line 4, in <module>
    import dlib
  File "/usr/local/lib/python3.8/site-packages/dlib/__init__.py", line 19, in <module>
    from _dlib_pybind11 import *
ImportError: /usr/local/lib/python3.8/site-packages/_dlib_pybind11.cpython-38-aarch64-linux-gnu.so: undefined symbol: png_riffle_palette_neon

This is the compreface section within config.yaml

compreface:
  face_recognition:
    host: !secret compreface_host
    port: 8000
    recognition_api_key: !secret compreface_api_key
    train: true
    face_plugins: age,gender
    cameras:
      camera_2:
    labels:
      - person

Additionally, does Viseron not use any prexisting face collections in Compreface? The component doc states that faces are loaded from the face_recognition_path and a model is built.

Thanks and regards.

[roflcoopter]

Looking into it, running some new builds as we speak but it takes some time for them to complete

[roflcoopter]

Should be fixed now if you pull the latest version of roflcoopter/jetson-nano-viseron:dev

Please try it out when you get some time and let me know how it goes.

Additionally, does Viseron not use any prexisting face collections in Compreface? The component doc states that faces are loaded from the face_recognition_path and a model is built.

You need to tell Viseron what people to track using the face_recognition_path, yes. However you can just opt to set train: false and use your already trained model, but you still need the folder structure for Viseron to pick up the names of people.
Now that you mention it, it sounds kind of weird, would be a lot smoother if it would fetch the trained faces from the API.
Will add that in a future release.

[gofaster]

The latest dev build starts up without errors when Compreface is enabled. Thank you for responding so quickly and for clarifying the role of existing collections.

[gofaster]

I noticed that the following error pops up intermittently and randomly for the 2 cameras that I'm testing with Compreface face recognition. It could occur singly or in bursts. I can't discern a pattern as to when or how. Not sure where to dig further.

[2022-11-28 11:48:33] [ERROR   ] [viseron.components.compreface.face_recognition.camera_3] - Error calling compreface: OpenCV(4.5.5) /tmp/opencv/modules/imgcodecs/src/loadsave.cpp:976: error: (-215:Assertion failed) !image.empty() in function 'imencode'
Traceback (most recent call last):
  File "/src/viseron/components/compreface/face_recognition.py", line 96, in face_recognition
    cv2.imencode(".jpg", cropped_frame)[1].tobytes(),
cv2.error: OpenCV(4.5.5) /tmp/opencv/modules/imgcodecs/src/loadsave.cpp:976: error: (-215:Assertion failed) !image.empty() in function 'imencode'

This is with current jetson-nano-viseron:dev digest:84f687c18425...
Please let me know if I should create a new thread for this question.

[roflcoopter]

I just got this error locally as well, i think it happens when you have an object which is very close to the edge of the image, which could case the relative coordinates to be negative.

Will push an update soon and see if it resolves your issue as well.

[roflcoopter]

If you pull the dev tag now i think it should be fixed

[gofaster]

I'm happy to report that after 21+ hours with with current dev build, the error has not appeared at all . Thanks!

Very intermittently, some uncaught exceptions pop up - usually relating to "concat_segments". Should I report those?

[roflcoopter]

Should be fixed now in dev.

I had a hard time reproducing so please test it out when you get the chance

[gofaster]

Will monitor the log. Thank you again.

[gofaster]

This is probably not too helpful as I had disabled DEBUG logging.

[...]
[2022-12-11 13:31:31] [INFO    ] [viseron.components.nvr.nvr.camera_3] - Stopping recording in: 1
[2022-12-11 13:31:32] [INFO    ] [viseron.components.nvr.nvr.camera_3] - Stopping recording in: 0
[2022-12-11 13:31:32] [INFO    ] [viseron.components.gstreamer.recorder.camera_3] - Stopping recorder
[2022-12-11 13:31:37] [INFO    ] [viseron.components.gstreamer.recorder.camera_3] - Starting recorder
[2022-12-11 13:31:38] [WARNING ] [viseron.components.gstreamer.recorder.camera_3] - Could not find matching start segment. Using earliest possible
pipe:: Operation not permitted
[2022-12-11 13:31:39] [ERROR   ] [viseron.components.gstreamer.recorder.camera_3] - Failed to concatenate segments: Command '['ffmpeg', '-hide_banner', '-loglevel', 'error', '-y', '-protocol_whitelist', 'file,pipe', '-f', 'concat', '-safe', '0', '-i', '-', '-c:v', 'copy', '-c:a', 'copy', '-movflags', '+faststart', '/recordings/camera_3/2022-12-11/13:31:11.mp4']' returned non-zero exit status 1.
[2022-12-11 13:31:39] [INFO    ] [viseron.components.nvr.nvr.camera_3] - Stopping recording in: 9
[2022-12-11 13:31:41] [INFO    ] [viseron.components.nvr.nvr.camera_3] - Stopping recording in: 8
[...]

[roflcoopter]

Yes would be helpful with debug logs.
Does it happen consistently or intermittently?

[gofaster]

Very intermittent, like 0-2 occurrences a day. Will increase logging level.