onnx利用openvino2019模型转化为IR出现不匹配

[123410]

[ ERROR ] Unexpected exception happened. [ ERROR ] Please contact Model Optimizer developers and forward the following information: [ ERROR ] Exception occurred during running replacer "REPLACEMENT_ID ()": After re-inference of 2933 node, old and new shapes do not match. Old shapes: [array([ 1, 3, 80, 80, 5])], new shapes: [array([ 1, 3, 80, 80, 14])]. [ ERROR ] Traceback (most recent call last): File "/opt/intel/2019_r1/openvino_2019.1.094/deployment_tools/model_optimizer/mo/utils/class_registration.py", line 167, in apply_replacements replacer.find_and_replace_pattern(graph) File "/opt/intel/2019_r1/openvino_2019.1.094/deployment_tools/model_optimizer/mo/utils/replacement_pattern.py", line 29, in find_and_replace_pattern apply_pattern(graph, **self.pattern(), action=self.replace_pattern) # pylint: disable=no-member File "/opt/intel/2019_r1/openvino_2019.1.094/deployment_tools/model_optimizer/mo/middle/pattern_match.py", line 95, in apply_pattern action(graph, match) File "/opt/intel/2019_r1/openvino_2019.1.094/deployment_tools/model_optimizer/extensions/middle/SliceConverter.py", line 100, in replace_pattern ss.create_node_with_data(inputs=[input, begin_node, end_node], data_nodes=[output_data]) File "/opt/intel/2019_r1/openvino_2019.1.094/deployment_tools/model_optimizer/mo/ops/op.py", line 213, in create_node_with_data [data_node.shape for data_node in data_nodes]) AssertionError: After re-inference of 2933 node, old and new shapes do not match. Old shapes: [array([ 1, 3, 80, 80, 5])], new shapes: [array([ 1, 3, 80, 80, 14])]. The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/opt/intel/2019_r1/openvino_2019.1.094/deployment_tools/model_optimizer/mo/main.py", line 312, in main return driver(argv) File "/opt/intel/2019_r1/openvino_2019.1.094/deployment_tools/model_optimizer/mo/main.py", line 289, in driver ret_res = mo_onnx.driver(argv, argv.input_model, model_name, argv.output_dir) File "/opt/intel/2019_r1/openvino_2019.1.094/deployment_tools/model_optimizer/mo/pipeline/onnx.py", line 87, in driver class_registration.apply_replacements(graph, class_registration.ClassType.MIDDLE_REPLACER) File "/opt/intel/2019_r1/openvino_2019.1.094/deployment_tools/model_optimizer/mo/utils/class_registration.py", line 190, in apply_replacements )) from err Exception: Exception occurred during running replacer "REPLACEMENT_ID ()": After re-inference of 2933 node, old and new shapes do not match. Old shapes: [array([ 1, 3, 80, 80, 5])], new shapes: [array([ 1, 3, 80, 80, 14])]. [ ERROR ] ---------------- END OF BUG REPORT -------------- [ ERROR ] -------------------------------------------------

[Megat_Intel]

Hi 123410,

Thank you for reaching out to us.

Based on the error message you provided, the issue seems to be a bug in the old OpenVINO™ 2019.1.0 version as discussed in this GitHub issue https://github.com/openvinotoolkit/openvino/issues/133. This bug has already been fixed and merged into the later version.

For us to validate the exact issue you are facing, could you provide us with the ONNX model that you are converting? Please provide us with the additional details below:

• Operating System
• CPU / GPU details
• Model Optimizer command

On the other hand, are there any specific reasons for using the old OpenVINO™ 2019 version? We recommend that you update your OpenVINO™ Toolkit version to the latest 2024 version, as it includes all the latest bug fixes and improvements.

Regards,

Megat

[Megat_Intel]

Hi 123410,

Thank you for your question. This thread will no longer be monitored since we have provided a suggestion. If you need any additional information from Intel, please submit a new question. 

Regards,

Megat