I try to custom yolov8x but it got error as following. Cloud you solve this?
(env) bay@DESKTOP-EE29K9L:~$ hailomz compile yolov8x --ckpt=/home/bay/data/yolov8x_enco_doh-100epoch.onnx --hw-arch hailo8 --calib-path /home/bay/data/enco_mtmc_multiple_augmented_images --classes 11
<Hailo Model Zoo INFO> Start run for network yolov8x ...
<Hailo Model Zoo INFO> Initializing the hailo8 runner...
[info] Translation started on ONNX model yolov8x
[info] Restored ONNX model yolov8x (completion time: 00:00:01.97)
[info] Extracted ONNXRuntime meta-data for Hailo model (completion time: 00:00:11.83)
[info] NMS structure of yolov8 (or equivalent architecture) was detected.
[info] In order to use HailoRT post-processing capabilities, these end node names should be used: /model.22/cv2.0/cv2.0.2/Conv /model.22/cv3.0/cv3.0.2/Conv /model.22/cv2.1/cv2.1.2/Conv /model.22/cv3.1/cv3.1.2/Conv /model.22/cv2.2/cv2.2.2/Conv /model.22/cv3.2/cv3.2.2/Conv.
[info] Start nodes mapped from original model: 'images': 'yolov8x/input_layer1'.
[info] End nodes mapped from original model: '/model.22/cv2.0/cv2.0.2/Conv', '/model.22/cv3.0/cv3.0.2/Conv', '/model.22/cv2.1/cv2.1.2/Conv', '/model.22/cv3.1/cv3.1.2/Conv', '/model.22/cv2.2/cv2.2.2/Conv', '/model.22/cv3.2/cv3.2.2/Conv'.
[info] Translation completed on ONNX model yolov8x (completion time: 00:00:14.84)
[info] Saved HAR to: /home/bay/yolov8x.har
<Hailo Model Zoo INFO> Preparing calibration data...
[info] Loading model script commands to yolov8x from /home/bay/hailo_model_zoo/hailo_model_zoo/cfg/alls/generic/yolov8x.alls
[info] Loading model script commands to yolov8x from string
[info] The layer yolov8x/conv73 was detected as reg_layer.
[info] The layer yolov8x/conv88 was detected as reg_layer.
[info] The layer yolov8x/conv100 was detected as reg_layer.
[info] Starting Model Optimization
[info] Using default optimization level of 2
[info] Using default compression level of 1
[info] Model received quantization params from the hn
[info] Starting Mixed Precision
[info] Assigning 4bit weights to layer yolov8x/conv41 with 3686.40k parameters
[info] Assigning 4bit weights to layer yolov8x/conv83 with 3686.40k parameters
[info] Assigning 4bit weights to layer yolov8x/conv26 with 1843.20k parameters
[info] Assigning 4bit weights to layer yolov8x/conv85 with 1843.20k parameters
[info] Assigning 4bit weights to layer yolov8x/conv101 with 1843.20k parameters
[info] Assigning 4bit weights to layer yolov8x/conv40 with 1638.40k parameters
[info] Ratio of weights in 4bit is 0.21
[info] Mixed Precision is done (completion time is 00:00:00.08)
[info] create_layer_norm skipped
[info] Starting Stats Collector
[info] Using dataset with 2800 entries for calibration
Calibration: 100%|█████████████████████████████████████████████████████| 2800/2800 [06:08<00:00, 7.60entries/s]
[info] Stats Collector is done (completion time is 00:06:13.25)
[info] No shifts available for layer yolov8x/conv29/conv_op, using max shift instead. delta=0.18992049859499804
[info] No shifts available for layer yolov8x/conv29/conv_op, using max shift instead. delta=0.094960198881334
[info] No shifts available for layer yolov8x/conv49/conv_op, using max shift instead. delta=0.3812496882783414
[info] No shifts available for layer yolov8x/conv49/conv_op, using max shift instead. delta=0.1906248825103667
[info] No shifts available for layer yolov8x/conv58/conv_op, using max shift instead. delta=0.5873108429438831
[info] No shifts available for layer yolov8x/conv58/conv_op, using max shift instead. delta=0.29365534702416785
[info] No shifts available for layer yolov8x/conv101/conv_op, using max shift instead. delta=0.1815524716857313
[info] No shifts available for layer yolov8x/conv103/conv_op, using max shift instead. delta=0.5374199133004813
Traceback (most recent call last):
File "/home/bay/env/bin/hailomz", line 33, in <module>
sys.exit(load_entry_point('hailo-model-zoo', 'console_scripts', 'hailomz')())
File "/home/bay/hailo_model_zoo/hailo_model_zoo/main.py", line 122, in main
run(args)
File "/home/bay/hailo_model_zoo/hailo_model_zoo/main.py", line 111, in run
return handlers[args.command](args)
File "/home/bay/hailo_model_zoo/hailo_model_zoo/main_driver.py", line 250, in compile
_ensure_optimized(runner, logger, args, network_info)
File "/home/bay/hailo_model_zoo/hailo_model_zoo/main_driver.py", line 91, in _ensure_optimized
optimize_model(
File "/home/bay/hailo_model_zoo/hailo_model_zoo/core/main_utils.py", line 326, in optimize_model
runner.optimize(calib_feed_callback)
File "/home/bay/env/lib/python3.10/site-packages/hailo_sdk_common/states/states.py", line 16, in wrapped_func
return func(self, *args, **kwargs)
File "/home/bay/env/lib/python3.10/site-packages/hailo_sdk_client/runner/client_runner.py", line 1674, in optimize
self._optimize(calib_data, data_type=data_type, work_dir=work_dir)
File "/home/bay/env/lib/python3.10/site-packages/hailo_sdk_common/states/states.py", line 16, in wrapped_func
return func(self, *args, **kwargs)
File "/home/bay/env/lib/python3.10/site-packages/hailo_sdk_client/runner/client_runner.py", line 1542, in _optimize
self._sdk_backend.full_quantization(calib_data, data_type=data_type, work_dir=work_dir)
File "/home/bay/env/lib/python3.10/site-packages/hailo_sdk_client/sdk_backend/sdk_backend.py", line 910, in full_quantization
self._full_acceleras_run(self.calibration_data, data_type)
File "/home/bay/env/lib/python3.10/site-packages/hailo_sdk_client/sdk_backend/sdk_backend.py", line 1034, in _full_acceleras_run
optimization_flow.run()
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/flows/optimization_flow.py", line 246, in run
self.step1()
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/tools/subprocess_wrapper.py", line 57, in parent_wrapper
raise SubprocessTracebackFailure(*child_messages)
hailo_model_optimization.acceleras.utils.acceleras_exceptions.SubprocessTracebackFailure: Subprocess failed with traceback
Traceback (most recent call last):
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/tools/subprocess_wrapper.py", line 32, in child_wrapper
func(self, *args, **kwargs)
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/flows/optimization_flow.py", line 256, in step1
self.core_quantization()
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/flows/optimization_flow.py", line 298, in core_quantization
self._create_hw_params()
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/flows/optimization_flow.py", line 335, in _create_hw_params
create_hw_params.run()
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/algorithms/optimization_algorithm.py", line 47, in run
return super().run()
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/algorithms/algorithm_base.py", line 120, in run
self._run_int()
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/algorithms/create_hw_params/create_hw_params.py", line 318, in _run_int
comp_to_retry = self._create_hw_params_component(matching_component_group)
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/algorithms/create_hw_params/create_hw_params.py", line 197, in _create_hw_params_component
retry_negative_exp_list = self._hanlde_negative_exponent(layer, matching_component_group)
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/algorithms/create_hw_params/create_hw_params.py", line 209, in _hanlde_negative_exponent
algo.run()
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/algorithms/optimization_algorithm.py", line 47, in run
return super().run()
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/algorithms/algorithm_base.py", line 120, in run
self._run_int()
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/algorithms/neg_exponent_fixer/neg_exp_fixer.py", line 70, in _run_int
l_fix = self.fix_output(l_fix)
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/algorithms/neg_exponent_fixer/neg_exp_fixer.py", line 116, in fix_output
self._log_negative_exponent_shift(l_fix)
File "/home/bay/env/lib/python3.10/site-packages/hailo_model_optimization/algorithms/neg_exponent_fixer/neg_exp_fixer.py", line 186, in _log_negative_exponent_shift
raise NegativeSlopeExponentNonFixable(
hailo_model_optimization.acceleras.utils.acceleras_exceptions.NegativeSlopeExponentNonFixable: Quantization failed in layer yolov8x/conv103 due to unsupported required slope. Desired shift is 21.0, but op has only 8 data bits. This error raises when the data or weight range are not balanced. Mostly happens when using random calibration-set/weights, the calibration-set is not normalized properly or batch-normalization was not used during training.