用户您好，请详细描述您所遇到的问题。
1.硬件获取渠道：企业采购
2.当前系统镜像版本：ai_toolchain_centos_7_j5:v1.1.7
3.当前天工开物版本：-
4.问题定位：ssd_mobilenet_v1 tf模型转onnx模型之后，使用hb_mapper checher检查模型报错
2022-08-26 10:30:25,858 file: hb_mapper.py func: hb_mapper line No: 73 Start hb_mapper…
2022-08-26 10:30:25,858 file: hb_mapper.py func: hb_mapper line No: 74 log will be stored in /open_explorer/ddk/samples/ai_toolchain/horizon_model_convert_sample/09_qiupeng_test_model/forzen_inference_graph/mapper/hb_mapper_checker.log
2022-08-26 10:30:25,858 file: hb_mapper.py func: hb_mapper line No: 75 hbdk version 3.29.2
2022-08-26 10:30:25,858 file: hb_mapper.py func: hb_mapper line No: 76 horizon_nn version 0.13.6
2022-08-26 10:30:25,858 file: hb_mapper.py func: hb_mapper line No: 77 hb_mapper version 1.7.4
2022-08-26 10:30:25,925 file: helper.py func: helper line No: 124 Model input names: [‘image_tensor:0’]
2022-08-26 10:30:25,933 file: hb_mapper_checker.py func: hb_mapper_checker line No: 104 Model type: onnx
2022-08-26 10:30:25,933 file: hb_mapper_checker.py func: hb_mapper_checker line No: 105 march: bayes
2022-08-26 10:30:25,933 file: hb_mapper_checker.py func: hb_mapper_checker line No: 110 input names
2022-08-26 10:30:25,933 file: hb_mapper_checker.py func: hb_mapper_checker line No: 111 input shapes {}
2022-08-26 10:30:25,933 file: hb_mapper_checker.py func: hb_mapper_checker line No: 117 Begin model checking…
2022-08-26 10:30:25,933 file: build.py func: build line No: 36 [Fri Aug 26 10:30:25 2022] Start to Horizon NN Model Convert.
2022-08-26 10:30:25,933 file: dict_parser.py func: dict_parser line No: 28 The input parameter is not specified, convert with default parameters.
2022-08-26 10:30:25,934 file: dict_parser.py func: dict_parser line No: 518 Parsing the hbdk parameter:{‘hbdk_pass_through_params’: ‘–O0’}
2022-08-26 10:30:25,934 file: build.py func: build line No: 145 HorizonNN version: 0.13.6
2022-08-26 10:30:25,934 file: build.py func: build line No: 149 HBDK version: 3.29.2
2022-08-26 10:30:25,934 file: build.py func: build line No: 36 [Fri Aug 26 10:30:25 2022] Start to parse the onnx model.
2022-08-26 10:30:25,988 file: onnx_parser.py func: onnx_parser line No: 189 Input ONNX model infomation:
ONNX IR version: 5
Opset version: 10
Producer: tf2onnx1.10.1 a37f29
Domain: none
Input name: image_tensor:0, [1, 300, 300, 3]
Output name: …_boxes:0, [0, 0, 4]
Output name: …scores:0, [0, 0]
Output name: …lasses:0, [0, 0]
Output name: …ctions:0, [0]
2022-08-26 10:30:26,576 file: build.py func: build line No: 39 [Fri Aug 26 10:30:26 2022] End to parse the onnx model.
2022-08-26 10:30:26,587 file: build.py func: build line No: 268 Model input names: [‘image_tensor:0’]
2022-08-26 10:30:26,721 file: build.py func: build line No: 535 Saving the original float model: ./.hb_check/original_float_model.onnx.
2022-08-26 10:30:26,723 file: build.py func: build line No: 36 [Fri Aug 26 10:30:26 2022] Start to optimize the model.
2022-08-26 10:30:27,069 file: tool_utils.py func: tool_utils line No: 116 exception in command: checker
2022-08-26 10:30:27,071 file: tool_utils.py func: tool_utils line No: 117 Traceback (most recent call last):
File “/usr/local/lib/python3.6/site-packages/horizon_tc_ui/utils/tool_utils.py”, line 114, in __decorator
func(*args, **kargs)
File “/usr/local/lib/python3.6/site-packages/horizon_tc_ui/hb_mapper.py”, line 87, in checker
input_shape).run(__version__)
File “/usr/local/lib/python3.6/site-packages/horizon_tc_ui/hb_mapper_checker.py”, line 131, in run
**addtional_param)
File “/usr/local/lib/python3.6/site-packages/horizon_nn/build.py”, line 908, in check_onnx
return builder.build_model(original_model, save_model)
File “/usr/local/lib/python3.6/site-packages/horizon_nn/build.py”, line 541, in build_model
optimized_model = self.optimize_model(original_model)
File “/usr/local/lib/python3.6/site-packages/horizon_nn/build.py”, line 383, in optimize_model
self.node_dict)
File “/usr/local/lib/python3.6/site-packages/horizon_nn/horizon_onnx/quantizer.py”, line 189, in optimize
optimized_model_str = C.optimize(model_str, march, node_dict)
RuntimeError: There is an error in pass:constant_folding. Error message:Shape inference error(s): (op_type:Identity, node name: sub_graph_ending_node_Identity__52): [TypeInferenceError] Input 0 expected to have type but instead is null
(op_type:Gather, node name: Gather__60): [TypeInferenceError] Input 0 expected to have type but instead is null
2022-08-26 10:30:27,071 file: tool_utils.py func: tool_utils line No: 118 There is an error in pass:constant_folding. Error message:Shape inference error(s): (op_type:Identity, node name: sub_graph_ending_node_Identity__52): [TypeInferenceError] Input 0 expected to have type but instead is null
(op_type:Gather, node name: Gather__60): [TypeInferenceError] Input 0 expected to have type but instead is null
2022-08-26 10:30:27,071 file: build.py func: build line No: 39 [Fri Aug 26 10:30:27 2022] End to optimize the model.
2022-08-26 10:30:27,072 file: build.py func: build line No: 39 [Fri Aug 26 10:30:27 2022] End to Horizon NN Model Convert.