hailomz compile: ValueError: Tried to convert 'input' to a tensor and failed. Error: None values not supported.

I found the solution of this in this thread Problem With Model Optimization - #25 by Nadav

what you need to do is to add this line to the alls script
quantization_param([conv42, conv53, conv63], force_range_out=[0.0, 1.0])

for this do the following search this file in your docker container

add the line before nms line and save the file
quantization_param([conv42, conv53, conv63], force_range_out=[0.0, 1.0])

in the yaml file that you are passing through argument in the compile, for example this one
hailomz compile --ckpt yolov8m.onnx --calib-path /local/shared_with_docker/licence-plate/train/images/ --yaml hailo_model_zoo/cfg/networks/yolov8m.yaml --classes 1

modify the hailo_model_zoo/cfg/networks/yolov8m.yaml in your docker container

and change this

paths:
  network_path:
  - models_files/ObjectDetection/Detection-COCO/yolo/yolov8m/2023-02-02/yolov8m.onnx
  alls_script: yolov8m.alls
  url: https://hailo-model-zoo.s3.eu-west-2.amazonaws.com/ObjectDetection/Detection-COCO/yolo/yolov8m/2023-02-02/yolov8m.zip
alls_script: /the/path/to/the/file/that/you/changed/previusly

and re run the hailomz compile

you can find more information in the post shared.

1 Like