Unsupported layer logsoftmax in pytorch model while converting it to IR format using OpenVINO

[vkana3]

Hi 

I have created a model which has a log softmax layer at the end, I have trained and converted the model to onnx format.

But while converting it to IR format using OpenVINO I'm getting error as below:

[ ERROR ] 
[ ERROR ] It can happen due to bug in custom shape infer function <UNKNOWN>.
[ ERROR ] Or because the node inputs have incorrect values/shapes.
[ ERROR ] Or because input shapes are incorrect (embedded to the model or passed via --input_shape).
[ ERROR ] Run Model Optimizer with --log_level=DEBUG for more information.
[ ERROR ] There is no registered "infer" function for node "LogSoftmax_177" with op = "LogSoftmax". Please implement this function in the extensions. 
For more information please refer to Model Optimizer FAQ (https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_Model_Optimizer_FAQ.html), question #37. 
Stopped shape/value propagation at "LogSoftmax_177" node. 
For more information please refer to Model Optimizer FAQ (https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_Model_Optimizer_FAQ.html), question #38. 
Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.middle.PartialInfer.PartialInfer'>): There is no registered "infer" function for node "LogSoftmax_177" with op = "LogSoftmax". Please implement this function in the extensions. 
For more information please refer to Model Optimizer FAQ (https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_Model_Optimizer_FAQ.html), question #37. 
Stopped shape/value propagation at "LogSoftmax_177" node. 
For more information please refer to Model Optimizer FAQ (https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_Model_Optimizer_FAQ.html), question #38.

Can anyone please tell me how to solve this issue!

[Iffa_Intel]

Greetings,

First and foremost, before you try to convert, you need to ensure that the topology/models are supported by openvino. You can refer here: https://docs.openvinotoolkit.org/latest/openvino_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_ONNX.html

Once you are sure, you can refer to this video for detailed convertion progress: https://www.youtube.com/watch?v=cbdS3BjjbaQ

You can also refer to here if these models are relevant to yours:

1. https://docs.openvinotoolkit.org/latest/openvino_docs_MO_DG_prepare_model_convert_model_onnx_specific_Convert_Mask_RCNN.html
2. https://docs.openvinotoolkit.org/latest/openvino_docs_MO_DG_prepare_model_convert_model_onnx_specific_Convert_DLRM.html

Sincerely,

Iffa

[Iffa_Intel]

Greetings,

Intel will no longer monitor this thread since we have provided a solution. If you need any additional information from Intel, please submit a new question. 

Sincerely,

Iffa