用户您好，请详细描述您所遇到的问题：、
将hybridnets转onnx后，运行root@20371eeac7c9:/data# hb_mapper checker --model-type onnx --march bayes-e --model hybridnets_384x640_nhwc.onnx
卡在这里12分钟
2025-03-04 15:37:55,290 file: tool_utils.py func: tool_utils line No: 77 log will be stored in /data/hb_mapper_checker.log
2025-03-04 15:37:55,292 file: hb_mapper.py func: hb_mapper line No: 72 Start hb_mapper…
2025-03-04 15:37:55,293 file: hb_mapper.py func: hb_mapper line No: 73 hbdk version 3.49.14
2025-03-04 15:37:55,293 file: hb_mapper.py func: hb_mapper line No: 74 horizon_nn version 1.0.6.3
2025-03-04 15:37:55,294 file: hb_mapper.py func: hb_mapper line No: 75 hb_mapper version 1.23.8
2025-03-04 15:37:55,716 file: onnx_parser.py func: onnx_parser line No: 39 Model input names: [‘input’]
2025-03-04 15:37:55,732 file: hb_mapper_checker.py func: hb_mapper_checker line No: 106 Model type: onnx
2025-03-04 15:37:55,733 file: hb_mapper_checker.py func: hb_mapper_checker line No: 107 march: bayes-e
2025-03-04 15:37:55,734 file: hb_mapper_checker.py func: hb_mapper_checker line No: 112 input names
2025-03-04 15:37:55,735 file: hb_mapper_checker.py func: hb_mapper_checker line No: 113 input shapes {}
2025-03-04 15:37:55,735 file: hb_mapper_checker.py func: hb_mapper_checker line No: 119 Begin model checking…
2025-03-04 15:37:55,749 file: build.py func: build line No: 36 Start to Horizon NN Model Convert.
2025-03-04 15:37:55,750 file: model_debug.py func: model_debug line No: 61 Loading horizon_nn debug methods:
2025-03-04 15:37:55,751 file: build.py func: build line No: 146 The specified model compilation architecture: bayes-e.
2025-03-04 15:37:55,752 file: build.py func: build line No: 148 The specified model compilation optimization parameters: .
2025-03-04 15:37:56,718 file: build.py func: build line No: 36 Start to prepare the onnx model.
2025-03-04 15:37:56,719 file: utils.py func: utils line No: 53 Input ONNX Model Information:
ONNX IR version: 6
Opset version: [‘ai.onnx v11’, ‘horizon v1’]
Producer: pytorch v2.4.1
Domain: None
Model version: None
Graph input:
input: shape=[1, 3, 384, 640], dtype=FLOAT32
Graph output:
regression: shape=[‘Concatregression_dim_0’, ‘Concatregression_dim_1’, ‘Concatregression_dim_2’], dtype=FLOAT32
…fication: shape=[‘Sigmoidclassification_dim_0’, ‘Sigmoidclassification_dim_1’, ‘Sigmoidclassification_dim_2’], dtype=FLOAT32
…entation: shape=[‘Transposesegmentation_dim_0’, ‘Transposesegmentation_dim_1’, ‘Transposesegmentation_dim_2’, 3], dtype=FLOAT32
2025-03-04 15:38:00,979 file: build.py func: build line No: 39 End to prepare the onnx model.
2025-03-04 15:38:04,664 file: build.py func: build line No: 197 Saving model: ./.hb_check/original_float_model.onnx.
2025-03-04 15:38:04,683 file: build.py func: build line No: 36 Start to optimize the model.
2025-03-04 15:38:16,999 file: build.py func: build line No: 39 End to optimize the model.
2025-03-04 15:38:17,010 file: build.py func: build line No: 39 End to Horizon NN Model Convert.
这里是日志内容
1. 板卡型号及板卡外观图片：RDK X3，RDK X3 Module，RDK X5，RDK X5 Module，RDK Ultra，RDK S100，等等
- 提供 sudo cat /etc/version 命令的返回结果-
- 提供 sudo rdkos_info 命令的返回结果
2.天工开物开发包OpenExplorer版本：例如XJ3_OE_2.4.2，XJ3_OE_1.15.2，J5_OE_1.1.40等
3.问题定位：例如模型转换