Unexpected error on model optimization

General
1

Hi all, I am currently trying to convert a Depth Anything model to HEF and I keep running into this error.

The command I’m running:

hailo optimize ./depth_anything_v2_vitb_indoor_dynamic.har --use-random-calib-set

The error:

[info] Using dataset with 64 entries for calibration
Calibration:   0%|                                                                                                           | 0/64 [00:00<?, ?entries/s]Traceback (most recent call last):
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/bin/hailo", line 8, in <module>
    sys.exit(main())
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_platform/tools/hailocli/main.py", line 116, in main
    return a.run()
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_platform/tools/hailocli/main.py", line 64, in run
    ret_val = self._run(argv)
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_platform/tools/hailocli/main.py", line 111, in _run
    return args.func(args)
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_sdk_client/tools/optimize_cli.py", line 120, in run
    self._runner.optimize(dataset, work_dir=args.work_dir)
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_sdk_common/states/states.py", line 16, in wrapped_func
    return func(self, *args, **kwargs)
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_sdk_client/runner/client_runner.py", line 2128, in optimize
    self._optimize(calib_data, data_type=data_type, work_dir=work_dir)
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_sdk_common/states/states.py", line 16, in wrapped_func
    return func(self, *args, **kwargs)
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_sdk_client/runner/client_runner.py", line 1970, in _optimize
    self._sdk_backend.full_quantization(calib_data, data_type=data_type, work_dir=work_dir)
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_sdk_client/sdk_backend/sdk_backend.py", line 1125, in full_quantization
    self._full_acceleras_run(self.calibration_data, data_type)
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_sdk_client/sdk_backend/sdk_backend.py", line 1319, in _full_acceleras_run
    optimization_flow.run()
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_model_optimization/tools/orchestator.py", line 306, in wrapper
    return func(self, *args, **kwargs)
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_model_optimization/flows/optimization_flow.py", line 335, in run
    step_func()
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_model_optimization/tools/orchestator.py", line 250, in wrapped
    result = method(*args, **kwargs)
  File "/home/bowling_jared/.local/share/virtualenvs/sc_depth_pl-MkbsLxzA/lib/python3.10/site-packages/hailo_model_optimization/tools/subprocess_wrapper.py", line 113, in parent_wrapper
    raise SubprocessUnexpectedFailure(
hailo_model_optimization.acceleras.utils.acceleras_exceptions.SubprocessUnexpectedFailure: Subprocess step1 failed with unexpected error. exitcode -11

Is this a resource issue perhaps? Unsure of what to do and the logs have no additional insights

2

Hey @Jared_Bowling,

Welcome to the Hailo Community!

This happens mostly because you have a random calibration set!

  1. Using hailo analyze before optimization:
    Running hailo analyze first to identify unsupported operations before attempting optimization. This helps prevent compilation failures.

  2. Calibration settings:
    Use a calibration set that you create.

For more info check out the DFC and model ZOO documentation in here: https://hailo.ai/developer-zone/software-downloads/