用户您好，请详细描述您所遇到的问题，详细的描述有助于帮助我们快速定位，解决问题~Thanks♪(･ω･)ﾉ
1. 芯片型号：J6E
2. 天工开物开发包 OpenExplorer 版本： J6_OE_V3.0.17
3. 问题定位：例如模型转换
2024-11-05 10:49:24,135 file: tool_utils.py func: tool_utils line No: 81 log will be stored in /open_explorer/hb_compile.log
2024-11-05 10:49:24,135 file: hb_compile.py func: hb_compile line No: 376 Start hb_compile...
2024-11-05 10:49:24,135 file: hb_compile.py func: hb_compile line No: 377 hbdk version: 4.0.25
2024-11-05 10:49:24,135 file: hb_compile.py func: hb_compile line No: 378 horizon_nn version: 2.0.4
2024-11-05 10:49:24,136 file: hb_compile.py func: hb_compile line No: 379 hb_compile version: 3.2.4
2024-11-05 10:49:24,148 file: yaml_builder.py func: yaml_builder line No: 71 {'model_parameters': {'layer_out_dump': False, 'working_dir': '.hb_compile'}, 'input_parameters': {'input_name': '', 'input_shape': '', 'input_space_and_range': '', 'input_type_rt': 'featuremap', 'input_type_train': 'featuremap', 'norm_type': 'no_preprocess'}, 'calibration_parameters': {'calibration_type': 'skip', 'per_channel': False, 'run_on_bpu': '', 'run_on_cpu': ''}, 'compiler_parameters': {'compile_mode': 'latency', 'core_num': 1, 'debug': True, 'jobs': 32, 'max_time_per_fc': 0, 'optimize_level': 'O0'}}
2024-11-05 10:49:24,148 file: yaml_builder.py func: yaml_builder line No: 72 check template yaml load success
2024-11-05 10:49:24,148 file: yaml_builder.py func: yaml_builder line No: 220 Updated yaml config info: {'model_parameters': {'layer_out_dump': False, 'working_dir': '/open_explorer/.hb_compile', 'onnx_model': '/open_explorer/reduce_max.onnx', 'march': 'nash-e', 'output_model_file_prefix': 'reduce_max'}, 'input_parameters': {'input_name': 'data;axes', 'input_shape': '3x2x2;1', 'input_space_and_range': '', 'input_type_rt': 'featuremap;featuremap', 'input_type_train': 'featuremap;featuremap', 'norm_type': 'no_preprocess;no_preprocess'}, 'calibration_parameters': {'calibration_type': 'skip', 'per_channel': False, 'run_on_bpu': '', 'run_on_cpu': ''}, 'compiler_parameters': {'compile_mode': 'latency', 'core_num': 1, 'debug': True, 'jobs': 32, 'max_time_per_fc': 0, 'optimize_level': 'O0'}}
2024-11-05 10:49:24,151 file: hb_compile.py func: hb_compile line No: 37 Start verifying yaml
2024-11-05 10:49:24,156 file: params_parser.py func: params_parser line No: 157 Using onnx model file: /open_explorer/reduce_max.onnx
2024-11-05 10:49:24,156 file: onnx_parser.py func: onnx_parser line No: 39 Model input names: ['data', 'axes']
2024-11-05 10:49:24,156 file: params_parser.py func: params_parser line No: 167 Model has 2 inputs according to model file
2024-11-05 10:49:24,156 file: params_parser.py func: params_parser line No: 323 node_dict: {}
2024-11-05 10:49:24,156 file: params_parser.py func: params_parser line No: 416 Input shape [3, 2, 2] has length: 3, make sure it is a featuremap input
2024-11-05 10:49:24,156 file: params_parser.py func: params_parser line No: 416 Input shape [1] has length: 1, make sure it is a featuremap input
2024-11-05 10:49:24,156 file: params_parser.py func: params_parser line No: 661 Parameter calibration_type is skip. cal_data_dir check skipped
2024-11-05 10:49:24,156 file: params_parser.py func: params_parser line No: 793 Input node data's input_source not set, it will be set to None by default
2024-11-05 10:49:24,156 file: params_parser.py func: params_parser line No: 793 Input node axes's input_source not set, it will be set to None by default
2024-11-05 10:49:24,156 file: params_parser.py func: params_parser line No: 855 Parameter compile_mode is set to latency, balance_factor will set to 100.
2024-11-05 10:49:24,157 file: params_parser.py func: params_parser line No: 895 custom_op does not exist, skipped
2024-11-05 10:49:24,157 file: hb_compile.py func: hb_compile line No: 40 End verifying yaml
2024-11-05 10:49:24,157 file: ptq_model_builder.py func: ptq_model_builder line No: 241 quantize_params is {'cali_dict': {'calibration_type': 'max', 'quant_config': None}, 'input_dict': {'data': {'input_shape': [3, 2, 2]}, 'axes': {'input_shape': [1]}}, 'node_dict': {}, 'debug_methods': [], 'output_nodes': [], 'optimization_methods': None, 'quant_config': None}
2024-11-05 10:49:24,157 file: wrap_utils.py func: wrap_utils line No: 15 Start to execute horizon_nn.api.build_model.
2024-11-05 10:49:24,157 file: model_builder.py func: model_builder line No: 32 Start to Horizon NN Model Convert.
2024-11-05 10:49:24,157 file: model_debugger.py func: model_debugger line No: 66 Loading horizon_nn debug methods:[]
2024-11-05 10:49:24,157 file: model_builder.py func: model_builder line No: 189 The specified model compilation architecture: nash.
2024-11-05 10:49:24,157 file: model_builder.py func: model_builder line No: 193 The specified model compilation optimization parameters: [].
2024-11-05 10:49:24,157 file: model_builder.py func: model_builder line No: 32 Start to prepare the onnx model.
2024-11-05 10:49:24,158 file: prepare.py func: prepare line No: 145 Input ONNX Model Information:
ONNX IR version: 8
Opset version: ['ai.onnx v18', 'horizon v1']
Producer: backend-test
Domain: None
Model version: None
Graph input:
data: shape=[3, 2, 2], dtype=FLOAT32
axes: shape=[1], dtype=INT64
Graph output:
reduced: shape=[3, 1, 2], dtype=FLOAT32
2024-11-05 10:49:24,168 file: prepare.py func: prepare line No: 42 The original model's opset version is 18, try converting to opset 19.
2024-11-05 10:49:24,172 file: model_builder.py func: model_builder line No: 35 End to prepare the onnx model.
2024-11-05 10:49:24,172 file: model_builder.py func: model_builder line No: 239 Saving model to: /open_explorer/.hb_compile/reduce_max_original_float_model.onnx.
2024-11-05 10:49:24,172 file: model_builder.py func: model_builder line No: 32 Start to optimize the onnx model.
2024-11-05 10:49:24,174 file: model_builder.py func: model_builder line No: 35 End to optimize the onnx model.
2024-11-05 10:49:24,175 file: model_builder.py func: model_builder line No: 239 Saving model to: /open_explorer/.hb_compile/reduce_max_optimized_float_model.onnx.
2024-11-05 10:49:24,175 file: model_builder.py func: model_builder line No: 32 Start to calibrate the model.
2024-11-05 10:49:24,176 file: calibration_data_set.py func: calibration_data_set line No: 82 input name: data, number_of_samples: 1
2024-11-05 10:49:24,176 file: calibration_data_set.py func: calibration_data_set line No: 82 input name: axes, number_of_samples: 1
2024-11-05 10:49:24,176 file: calibration_data_set.py func: calibration_data_set line No: 96 There are 1 samples in the calibration data set.
2024-11-05 10:49:24,176 file: fixed_calibrater.py func: fixed_calibrater line No: 31 Run calibration model with fixed thresholds method.
2024-11-05 10:49:24,178 file: model_builder.py func: model_builder line No: 35 End to calibrate the model.
2024-11-05 10:49:24,179 file: model_builder.py func: model_builder line No: 239 Saving model to: /open_explorer/.hb_compile/reduce_max_calibrated_model.onnx.
2024-11-05 10:49:24,179 file: model_builder.py func: model_builder line No: 32 Start to precompile the model.
2024-11-05 10:49:24,183 file: model_builder.py func: model_builder line No: 35 End to precompile the model.
2024-11-05 10:49:24,184 file: model_builder.py func: model_builder line No: 239 Saving model to: /open_explorer/.hb_compile/reduce_max_ptq_model.onnx.
2024-11-05 10:49:24,203 file: model_builder.py func: model_builder line No: 35 End to Horizon NN Model Convert.
2024-11-05 10:49:24,203 file: wrap_utils.py func: wrap_utils line No: 18 End to execute horizon_nn.api.build_model.
2024-11-05 10:49:24,203 file: wrap_utils.py func: wrap_utils line No: 15 Start to execute hbdk.export.
2024-11-05 10:49:24,204 file: tool_utils.py func: tool_utils line No: 139 exception in command: main
2024-11-05 10:49:24,205 file: tool_utils.py func: tool_utils line No: 140 Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/horizon_tc_ui/utils/wrap_utils.py", line 17, in wrapper
result = func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/horizon_tc_ui/hbir_handle.py", line 54, in export_hbir
return export(proto=ptq_model, name=output_prefix_name)
File "/usr/local/lib/python3.10/dist-packages/hbdk4/compiler/onnx/__init__.py", line 40, in export
graph.emit_mlir_func_op(OpConvertorRegistry(), True)
File "/usr/local/lib/python3.10/dist-packages/hbdk4/compiler/frontend/adaptor.py", line 350, in emit_mlir_func_op
node_adaptor.emit_mlir_op(registry)
File "/usr/local/lib/python3.10/dist-packages/hbdk4/compiler/frontend/adaptor.py", line 203, in emit_mlir_op
raise e
File "/usr/local/lib/python3.10/dist-packages/hbdk4/compiler/frontend/adaptor.py", line 188, in emit_mlir_op
results = cvt.emit_mlir_op(self, *args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/hbdk4/compiler/onnx/opset18.py", line 36, in emit_mlir_op
axes = adaptor.operands[1].value.tolist()
AttributeError: 'hbdk4.compiler._mlir_libs._mlir.ir.BlockArgument' object has no attribute 'tolist'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/horizon_tc_ui/utils/tool_utils.py", line 137, in __decorator
func(*args, **kargs)
File "/usr/local/lib/python3.10/dist-packages/horizon_tc_ui/hb_compile.py", line 399, in main
check_mode(model, proto, march, input_shape)
File "/usr/local/lib/python3.10/dist-packages/horizon_tc_ui/hb_compile.py", line 338, in check_mode
hbm_build(conf, ptq_model)
File "/usr/local/lib/python3.10/dist-packages/horizon_tc_ui/hb_compile.py", line 239, in hbm_build
hbm_builder.build()
File "/usr/local/lib/python3.10/dist-packages/horizon_tc_ui/compile/hbm_builder.py", line 234, in build
self.convert_model()
File "/usr/local/lib/python3.10/dist-packages/horizon_tc_ui/compile/hbm_builder.py", line 196, in convert_model
model = HBIRHandle.export_hbir(
File "/usr/local/lib/python3.10/dist-packages/horizon_tc_ui/utils/wrap_utils.py", line 22, in wrapper
raise ValueError(f"*** ERROR-OCCUR-DURING {module_info} ***," +
ValueError: *** ERROR-OCCUR-DURING hbdk.export ***, error message: 'hbdk4.compiler._mlir_libs._mlir.ir.BlockArgument' object has no attribute 'tolist'
2024-11-05 10:49:24,205 file: tool_utils.py func: tool_utils line No: 141 *** ERROR-OCCUR-DURING hbdk.export ***, error message: 'hbdk4.compiler._mlir_libs._mlir.ir.BlockArgument' object has no attribute 'tolist'
请问如何解决？
'/%3e%3cpath%20d='M8%200.5C12.1421%200.5%2015.5%203.85786%2015.5%208C15.5%2012.1421%2012.1421%2015.5%208%2015.5C3.85786%2015.5%200.5%2012.1421%200.5%208C0.5%203.85786%203.85786%200.5%208%200.5Z'%20fill='url(%23paint1_linear_0_45845)'%20stroke='white'/%3e%3cpath%20d='M10.0597%204.5332C10.031%204.5332%2010.0036%204.54817%209.98859%204.57313L8.09724%207.79442C8.02613%207.90046%207.84897%208.23731%207.5483%208.7875C7.37863%209.0969%207.25387%209.32771%207.17152%209.48615C7.1341%209.55727%207.0293%209.53855%207.01807%209.45871C6.97191%209.11936%206.89456%208.6066%206.78727%207.91793L6.2483%204.61804C6.24207%204.57812%206.20713%204.54942%206.16721%204.54942H4.28085C4.2297%204.54942%204.18977%204.59683%204.201%204.64798L5.71059%2012.1959C5.71808%2012.2346%205.75176%2012.2621%205.79044%2012.2621H7.46845C7.49715%2012.2621%207.52335%2012.2471%207.53832%2012.2234L12.1869%204.65796C12.2205%204.60307%2012.1806%204.5332%2012.117%204.5332H10.0597Z'%20fill='white'/%3e%3cdefs%3e%3clinearGradient%20id='paint0_linear_0_45845'%20x1='8.99711'%20y1='15.3526'%20x2='47.3575'%20y2='15.3526'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20stop-color='%23AF86FF'/%3e%3cstop%20offset='1'%20stop-color='%23774EFF'/%3e%3c/linearGradient%3e%3clinearGradient%20id='paint1_linear_0_45845'%20x1='1.1152'%20y1='15.1368'%20x2='15.3888'%20y2='15.1368'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20stop-color='%23AF86FF'/%3e%3cstop%20offset='1'%20stop-color='%23774EFF'/%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e)
