tópico Error Executing Ported Model in OpenVino na Intel® Distribution of OpenVINO™ Toolkit

Error Executing Ported Model in OpenVino

A__Siva — Wed, 10 Apr 2019 05:04:55 GMT

#1. Trained a Pytorch Model

#2. Converted it into ONNX format. Conversion to ONNX format is successful No Errors

#3. Used OpenVino Option to get the XML using Model Optimizer. The Model Optimizer Generates Required XML No Errors. All the layers mentioned in XML are Supported by OpenVino.

#4. Got this error while running the demo - [ERROR] MKLDNNGraph::CreateGraph: such topology cannot be compiled for dynamic batch.

With the XML this error cannot be compiled for dynamic batch returned

Any thoughts / suggestion to take it forward ?

Dear Siva,

Shubha_R_Intel — Thu, 11 Apr 2019 19:14:00 GMT

Dear Siva,

My guess is that your ONNX model has a layer which is not supported by Dynamic Batching. Or maybe you're trying to run this on MYRIAD - which is a problem since Dynamic Batching is only supported on CPU and GPU. Can you kindly check this documentation to see how its content may apply to your situation ? I'm not sure which demo you are running, but does it set KEY_DYN_BATCH_ENABLED as described in the code below?

https://docs.openvinotoolkit.org/latest/_docs_IE_DG_DynamicBatching.html

Thanks,

Shubha