Error while compile yolov5 from onnx to hef

General
,
1

i have a custom yolov5 model with single class

i feel i need to make changes in .alls

image
image1177×952 54.1 KB

pls help

hailomz compile yolov5s --hw-arch hailo8l --har /home/kenny/yolov5s.har --calib-path /home/kenny/images
Start run for network yolov5s …
Initializing the hailo8l runner…
Preparing calibration data…
[info] Loading model script commands to yolov5s from /home/kenny/hailo_model_zoo/hailo_model_zoo/cfg/alls/generic/yolov5s.alls
Traceback (most recent call last):
File “/home/kenny/hailodfc/bin/hailomz”, line 33, in
sys.exit(load_entry_point(‘hailo-model-zoo’, ‘console_scripts’, ‘hailomz’)())
File “/home/kenny/hailo_model_zoo/hailo_model_zoo/main.py”, line 122, in main
run(args)
File “/home/kenny/hailo_model_zoo/hailo_model_zoo/main.py”, line 111, in run
return handlersargs.command
File “/home/kenny/hailo_model_zoo/hailo_model_zoo/main_driver.py”, line 250, in compile
runner = _ensure_optimized(runner, logger, args, network_info)
File “/home/kenny/hailo_model_zoo/hailo_model_zoo/main_driver.py”, line 91, in _ensure_optimized
optimize_model(
File “/home/kenny/hailo_model_zoo/hailo_model_zoo/core/main_utils.py”, line 351, in optimize_model
optimize_full_precision_model(runner, calib_feed_callback, logger, model_script, resize, input_conversion, classes)
File “/home/kenny/hailo_model_zoo/hailo_model_zoo/core/main_utils.py”, line 337, in optimize_full_precision_model
runner.optimize_full_precision(calib_data=calib_feed_callback)
File “/home/kenny/hailodfc/lib/python3.10/site-packages/hailo_sdk_common/states/states.py”, line 16, in wrapped_func
return func(self, *args, **kwargs)
File “/home/kenny/hailodfc/lib/python3.10/site-packages/hailo_sdk_client/runner/client_runner.py”, line 2031, in optimize_full_precision
self._optimize_full_precision(calib_data=calib_data, data_type=data_type)
File “/home/kenny/hailodfc/lib/python3.10/site-packages/hailo_sdk_client/runner/client_runner.py”, line 2034, in _optimize_full_precision
self._sdk_backend.optimize_full_precision(calib_data=calib_data, data_type=data_type)
File “/home/kenny/hailodfc/lib/python3.10/site-packages/hailo_sdk_client/sdk_backend/sdk_backend.py”, line 1591, in optimize_full_precision
model, params = self._apply_model_modification_commands(model, params, update_model_and_params)
File “/home/kenny/hailodfc/lib/python3.10/site-packages/hailo_sdk_client/sdk_backend/sdk_backend.py”, line 1482, in _apply_model_modification_commands
model, params = command.apply(model, params, hw_consts=self.hw_arch.consts)
File “/home/kenny/hailodfc/lib/python3.10/site-packages/hailo_sdk_client/sdk_backend/script_parser/nms_postprocess_command.py”, line 397, in apply
self._update_config_file(hailo_nn)
File “/home/kenny/hailodfc/lib/python3.10/site-packages/hailo_sdk_client/sdk_backend/script_parser/nms_postprocess_command.py”, line 557, in _update_c
onfig_file self._layers_scope_addition(hailo_nn)
File “/home/kenny/hailodfc/lib/python3.10/site-packages/hailo_sdk_client/sdk_backend/script_parser/nms_postprocess_command.py”, line 600, in _layers_s
cope_addition bbox_decoder[field.value] = hailo_nn.get_layer_by_name(bbox_decoder[field.value]).name
File “/home/kenny/hailodfc/lib/python3.10/site-packages/hailo_sdk_common/hailo_nn/hailo_nn.py”, line 537, in get_layer_by_name
raise HailoNNException(f"The layer named {layer_name} doesn’t exist in the HN")
hailo_sdk_common.hailo_nn.exceptions.HailoNNException: The layer named conv63 doesn’t exist in the HN

2

Hey @user98,

The error hailo_sdk_common.hailo_nn.exceptions.HailoNNException: The layer named conv63 doesn't exist in the HN indicates that your compilation process is trying to reference a layer (conv63) that doesn’t exist in your custom YOLOv5 model.

You’ll need to modify your ALLS file to reference the correct layer name in your model. This typically happens when layer names have been changed during your training or conversion process.

To resolve this:

  1. Update the layer name in your ALLS file to match your model’s actual layer naming
  2. If you need assistance, please share your current ALLS file and information about the conv layers in your model

Also, did you run the optimization step after parsing and before compiling? This is a crucial step in the workflow that shouldn’t be skipped.