TypeError: expected str, bytes or os.PathLike object, not NoneType - ONNX to HEF

General
1

I’m trying to compile a YOLOv8m model to a .hef file using Hailo-8L, starting from an ONNX model.

Environment Setup:

  • Main working directory: /home/hailo/shared/
  • Command used:

bash

CopyEdit

hailomz compile yolov8m \
  --har /home/hailo/shared/yolov8m.har \
  --calib-path /home/hailo/shared/datasets/images/train \
  --hw-arch hailo8l

YAML File:

/home/hailo/shared/hailo_model_zoo/hailo_model_zoo/cfg/networks/yolov8m.yaml

yaml

CopyEdit

base:
  - base/yolov8.yaml

postprocessing:
  device_pre_post_layers:
    nms: true
  hpp: true

network:
  network_name: yolov8m

paths:
  network_path:
    - /home/hailo/shared/yolov8m.har
  alls_script: cfg/alls/generic/yolov8m.alls
  hef_name: yolov8m.hef
  output_dir: compiled_model_yolov8m

info:
  task: object detection
  input_shape: 640x640x3
  output_shape: 80x5x100
  operations: 78.93G
  parameters: 25.9M
  framework: pytorch
  training_data: coco train2017
  validation_data: coco val2017
  eval_metric: mAP
  full_precision_result: 49.9
  source: https://github.com/ultralytics/ultralytics
  license_url: https://github.com/ultralytics/ultralytics/blob/main/LICENSE
  license_name: AGPL-3.0

Model Script (.alls):

/home/hailo/shared/hailo_model_zoo/hailo_model_zoo/cfg/alls/generic/yolov8m.alls

python

CopyEdit

normalization1 = normalization([0.0, 0.0, 0.0], [255.0, 255.0, 255.0])
model_optimization_config(calibration, batch_size=2)
change_output_activation(conv58, sigmoid)
change_output_activation(conv71, sigmoid)
change_output_activation(conv83, sigmoid)
post_quantization_optimization(finetune, policy=enabled, learning_rate=0.000025)
nms_postprocess("/home/hailo/shared/hailo_model_zoo/hailo_model_zoo/cfg/postprocess_config/yolov8m_nms_config.json", meta_arch=yolov8, engine=cpu)

resources_param(max_apu_utilization=0.9, max_compute_16bit_utilization=0.9, max_compute_utilization=0.9, max_control_utilization=0.9, max_input_aligner_utilization=0.9, max_memory_utilization=0.85, max_utilization=0.0)

Postprocess Config (NMS):

/home/hailo/shared/hailo_model_zoo/hailo_model_zoo/cfg/postprocess_config/yolov8m_nms_config.json

json

CopyEdit

{
  "nms_scores_th": 0.2,
  "nms_iou_th": 0.7,
  "image_dims": [640, 640],
  "max_proposals_per_class": 100,
  "classes": 80,
  "regression_length": 16,
  "background_removal": false,
  "background_removal_index": 0,
  "bbox_decoders": [
    {
      "name": "bbox_decoder57",
      "stride": 8,
      "reg_layer": "conv57",
      "cls_layer": "conv58"
    },
    {
      "name": "bbox_decoder70",
      "stride": 16,
      "reg_layer": "conv70",
      "cls_layer": "conv71"
    },
    {
      "name": "bbox_decoder82",
      "stride": 32,
      "reg_layer": "conv82",
      "cls_layer": "conv83"
    }
  ]
}

Output & Error:

text

CopyEdit

[info] Model Optimization Algorithm Quantization-Aware Fine-Tuning is done (completion time is 00:05:16.93)
[info] Layer Noise Analysis skipped
[info] Model Optimization is done
[info] Saved HAR to: /home/hailo/shared/hailo_model_zoo/yolov8m.har
[info] Loading model script commands to yolov8m from /home/hailo/shared/hailo_model_zoo/hailo_model_zoo/cfg/alls/generic/yolov8m.alls
[info] ParsedPerformanceParam command, setting optimization_level(max=2)
[error] Failed to produce compiled graph
[error] TypeError: expected str, bytes or os.PathLike object, not NoneType

What I Tried:

  • Verified .har, .alls, and .json paths are correct.
  • Corrected post_quantization_optimization to use calibration instead of invalid finetune.
  • Ensured normalization values and NMS config are set properly.

Request:

Can someone confirm what typically causes the TypeError: expected str, bytes or os.PathLike object, not NoneType at the graph compilation step in this context? Is there a missing required path, output name, or value expected by the compiler?

Thanks in advance for your support.