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.

Running faster_rcnn pytorch model on NCS


Dear Experts,

I'm trying to get the pretrained object_recognition model fasterrcnn_resnet50_fpn of pytorch framework up and running on Intels NCS.
Therefore I exported the model from pytorch to onnx format. This was quite challenging but with the nightly build of pytorch an export was possible.
The problem is that the exported model uses opset_version=11 and I'm not able to convert the onnx model with to xml/bin format.

I'm getting following error message: Unexpected exception happened during extracting attributes for node Constant_111.

Perhaps someone can give a little hint I would very much appreciate your support.

I'm using Openvinco 2019_R3.1 and my environment looks as follows:

OS: Ubuntu 16.04.6 LTS
GCC version: (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609
CMake version: version 3.5.1

Python version: 3.7
Is CUDA available: No
CUDA runtime version: No CUDA
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA

Versions of relevant libraries:
[pip3] numpy==1.17.4
[pip3] torch==1.3.1
[pip3] torchvision==0.4.2
[conda] blas                      1.0                         mkl  
[conda] mkl                       2019.4                      243  
[conda] mkl-service               2.3.0            py37he904b0f_0  
[conda] mkl_fft                   1.0.14           py37ha843d7b_0  
[conda] mkl_random                1.1.0            py37hd6b4f25_0  
[conda] pytorch                   1.5.0.dev20200113 py3.7_cuda10.1.243_cudnn7.6.3_0    pytorch-nightly
[conda] torchvision               0.5.0.dev20200113      py37_cu101    pytorch-nightly

Kind regards,

0 Kudos
1 Reply

Hi Simon,


Thank you for reaching out.

I replied to you in another thread.



Javier A.

0 Kudos