Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6401 Discussions

Conversion problem for Pytorch MaxPool2d layer to Openvino

Neslihan_K_Intel
Employee
‎04-20-2020 01:11 AM
362 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

Link Copied

1 Reply
SuryaPSC_Intel
Employee
‎04-20-2020 04:31 AM
362 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

0 Kudos
Copy link
Reply

Community support is provided during standard business hours (Monday to Friday 7AM - 5PM PST). Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.