Hi @Michael
It is me who is grateful for your help, I did try multiple optimization levels but only 0 and 2 are working for me. Here is the error after setting it to 4:
info] No shifts available for layer yolov8s/conv24/conv_op, using max shift instead. delta=0.2283
[info] No shifts available for layer yolov8s/conv24/conv_op, using max shift instead. delta=0.1141
[info] No shifts available for layer yolov8s/conv56/conv_op, using max shift instead. delta=0.4500
[info] No shifts available for layer yolov8s/conv55/conv_op, using max shift instead. delta=0.1300
[info] No shifts available for layer yolov8s/conv55/conv_op, using max shift instead. delta=0.0650
[info] No shifts available for layer yolov8s/conv56/conv_op, using max shift instead. delta=0.2250
[info] No shifts available for layer yolov8s/conv56/conv_op, using max shift instead. delta=0.2250
[info] No shifts available for layer yolov8s/conv55/conv_op, using max shift instead. delta=0.0650
[info] No shifts available for layer yolov8s/conv58/conv_op, using max shift instead. delta=0.3486
[info] No shifts available for layer yolov8s/conv59/conv_op, using max shift instead. delta=0.3552
[info] No shifts available for layer yolov8s/conv59/conv_op, using max shift instead. delta=0.1776
[info] No shifts available for layer yolov8s/conv59/conv_op, using max shift instead. delta=0.1776
I0000 00:00:1773231826.885957 1259021 gpu_device.cc:2022] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 22337 MB memory: -> device: 0, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:01:00.0, compute capability: 8.6
I0000 00:00:1773231829.252390 1259021 gpu_device.cc:2022] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 22337 MB memory: -> device: 0, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:01:00.0, compute capability: 8.6
[info] Finetune encoding skipped
[info] Bias Correction skipped
[warning] Dataset is larger than dataset_size in Adaround. Increasing the algorithm dataset size might improve the results
[info] Starting Adaround
[info] The algorithm Adaround will use up to 31.88 GB of storage space
[info] Using dataset with 1024 entries for Adaround
[info] Using dataset with 64 entries for bias correction
Adaround: 0%| | 0/73 [00:00<?, ?blocks/s, Layers=['yolov8s/normalization1_output_0']]
Traceback (most recent call last):
File "/home/marcinc/.pyenv/versions/HailoDFC_3.32/bin/hailomz", line 33, in <module>
sys.exit(load_entry_point('hailo-model-zoo', 'console_scripts', 'hailomz')())
File "/opt/kiowa/hailo_model_zoo/hailo_model_zoo/main.py", line 122, in main
run(args)
File "/opt/kiowa/hailo_model_zoo/hailo_model_zoo/main.py", line 111, in run
return handlers[args.command](args)
File "/opt/kiowa/hailo_model_zoo/hailo_model_zoo/main_driver.py", line 248, in compile
_ensure_optimized(runner, logger, args, network_info)
File "/opt/kiowa/hailo_model_zoo/hailo_model_zoo/main_driver.py", line 91, in _ensure_optimized
optimize_model( File "/opt/kiowa/hailo_model_zoo/hailo_model_zoo/core/main_utils.py", line 353, in optimize_model
runner.optimize(calib_feed_callback)
File "/home/marcinc/.pyenv/versions/3.10.6/envs/HailoDFC_3.32/lib/python3.10/site-packages/hailo_sdk_common/states/states.py", line 16, in wrapped_func
return func(self, *args, **kwargs)
File "/home/marcinc/.pyenv/versions/3.10.6/envs/HailoDFC_3.32/lib/python3.10/site-packages/hailo_sdk_client/runner/client_runner.py", line 2206, in optimize
result = self._optimize(
File "/home/marcinc/.pyenv/versions/3.10.6/envs/HailoDFC_3.32/lib/python3.10/site-packages/hailo_sdk_common/states/states.py", line 16, in wrapped_func
return func(self, *args, **kwargs)
File "/home/marcinc/.pyenv/versions/3.10.6/envs/HailoDFC_3.32/lib/python3.10/site-packages/hailo_sdk_client/runner/client_runner.py", line 2025, in _optimize
checkpoint_info = self._sdk_backend.full_quantization(
File "/home/marcinc/.pyenv/versions/3.10.6/envs/HailoDFC_3.32/lib/python3.10/site-packages/hailo_sdk_client/sdk_backend/sdk_backend.py", line 1196, in full_quantization
new_checkpoint_info = self._full_acceleras_run(
File "/home/marcinc/.pyenv/versions/3.10.6/envs/HailoDFC_3.32/lib/python3.10/site-packages/hailo_sdk_client/sdk_backend/sdk_backend.py", line 1434, in _full_acceleras_run
new_checkpoint_info = self._optimization_flow_runner(optimization_flow, checkpoint_info)
File "/home/marcinc/.pyenv/versions/3.10.6/envs/HailoDFC_3.32/lib/python3.10/site-packages/hailo_sdk_client/sdk_backend/sdk_backend.py", line 2088, in _optimization_flow_runner
optimization_flow.run()
File "/home/marcinc/.pyenv/versions/3.10.6/envs/HailoDFC_3.32/lib/python3.10/site-packages/hailo_model_optimization/tools/orchestator.py", line 239, in wrapper
return func(self, *args, **kwargs)
File "/home/marcinc/.pyenv/versions/3.10.6/envs/HailoDFC_3.32/lib/python3.10/site-packages/hailo_model_optimization/flows/optimization_flow.py", line 357, in run
step_func()
File "/home/marcinc/.pyenv/versions/3.10.6/envs/HailoDFC_3.32/lib/python3.10/site-packages/hailo_model_optimization/tools/subprocess_wrapper.py", line 140, in parent_wrapper
raise SubprocessTracebackFailure(*child_messages)
hailo_model_optimization.acceleras.utils.acceleras_exceptions.SubprocessTracebackFailure: Subprocess failed with exception: in user code:
File "/home/marcinc/.pyenv/versions/3.10.6/envs/HailoDFC_3.32/lib/python3.10/site-packages/hailo_model_optimization/algorithms/block_by_block/block_by_block.py", line 217, in call_block *
result = block_model(inputs)
File "/home/marcinc/.pyenv/versions/3.10.6/envs/HailoDFC_3.32/lib/python3.10/site-packages/keras/src/utils/traceback_utils.py", line 122, in error_handler **
raise e.with_traceback(filtered_tb) from None
File "/home/marcinc/.pyenv/versions/3.10.6/envs/HailoDFC_3.32/lib/python3.10/site-packages/keras/src/layers/layer.py", line 1717, in update_shapes_dict_for_target_fn
raise ValueError(
ValueError: For a `build()` method with more than one argument, all arguments should have a `_shape` suffix and match an argument from `call()`. E.g. `build(self, foo_shape, bar_shape)` For layer 'HailoModel', Received `build()` argument `self`, which does not end in `_
shape`.
I am using DFC in version 3.32 if that helps.
