Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.
5541 Discussions

Conversion problem for Pytorch MaxPool2d layer to Openvino

Neslihan_K_Intel
Employee
140 Views

I would like to use pytorch MaxPool2d(kernel_size = 3, stride=1, padding=1) layer in OpenVino. I initially convert the layer to onnx format. However while converting to IR representation, I receive the following error:

failed:[ShapeInferenceError] Attribute pads has incorrect size

I tried also without padding and still receive the same error message.

I would like to learn if this Pytorch layer is supported in OpenVino or not. I will be glad if you can help me to solve the problem.

 

0 Kudos
1 Reply
SuryaPSC_Intel
Employee
140 Views

Hi Neslihan,

Can you please share the model architechture.

Also, please note that MaxPool2D operation is applied to the output of the previous layer, and cannot work without an input. So, kindly make sure to provide an input to the MaxPool2D operation.

Best Regards,

Surya

Reply