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.
6503 Discussions

Workbench does not have PyTorch option in Original Model->Framework

Tulipian
Beginner
518 Views

Installed

Docker OpenVINO™ DL Workbench 2021.4.2:

docker pull openvino/workbench:2021.4.2

 

But I do not see how to import my model which is in Pytorch, it's not in the dropbox (Import Model --> Original Model --> Framework).

Can someone help?

Tulipian_0-1658183352437.png

 

0 Kudos
2 Replies
Hairul_Intel
Moderator
496 Views

Hi Tulipian,

Thank you for reaching out to us.

 

For your information, the supported model format in OpenVINO™ Deep Learning (DL) Workbench are TensorFlow*, ONNX*, MXNet*, Caffe*, and OpenVINO™ Intermediate Representation (IR). Refer to the Import Original Model for more information.

 

On another note, if the model is from PyTorch framework, it is recommended to convert it to the ONNX format before importing the model into DL Workbench.

 

 

Regards,

Hairul


0 Kudos
Hairul_Intel
Moderator
474 Views

Hi Tulipian,

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

 

 

Regards,

Hairul


0 Kudos
Reply