Intel® DevCloud
Help for those needing help starting or connecting to the Intel® DevCloud
1596 Discussions

USE ONNX Problem

CLi37
Beginner
686 Views

I have ported a Tensorflow 2 model to work on DevCloud.

However my model can not be saved as a complete file, only the weight file can be saved.

Then how can I save it to an ONNX package for prediction and distribution? 

 

 

0 Kudos
1 Solution
Hari_B_Intel
Moderator
567 Views

Hi CLi37,


Thank for your patience and understanding, we have two examples of OpenVINO EP for ONNX Runtime.

Jupyter notebook -> Reference_samples -> iot-devcloud -> openvino-lts -> developer-samples -> python -> ONNX-Object-detection-python

and

Jupyter notebook -> Reference_samples -> iot-devcloud -> openvino-lts -> developer-samples -> onnx_openvino_classification

 

Both can be used with Python3 (OpenVINO 2021.4.2) Kernel

 

For your information, DevCloud is not meant for training and I don't think there is possible to generate the model.

You can still upload the complete save model to DevCloud for prediction and distribution.


Hope this information helps


Thank you


View solution in original post

0 Kudos
6 Replies
VaradJ_Intel
Moderator
662 Views

Hi,

 

Thanks for posting in Intel communities.

 

Please can you let us know which DevCloud are you using?

 

Thank you.

 

0 Kudos
CLi37
Beginner
646 Views

I use Intel JupyterLab with Intel Python and Tensorflow+ONNX kernel to train the model. I enabled ONNX with two-line codes.

I want to pack Python + Tensorflow trained model into the ONNX package and distribute on other ONNX devices? Any examples of doing so? 

0 Kudos
VaradJ_Intel
Moderator
634 Views

Hi,

 

Please can you share the Intel DevCloud that you are using? Is it Intel DevCloud for oneAPI or FPGA or Edge?

 

Thanks


0 Kudos
CLi37
Beginner
623 Views

It is Intel DevCould for the Edge. It is kernel is Python 3 (Tensorflow_OpenVINO 2022.1) in JuypterLab.

 

0 Kudos
Hari_B_Intel
Moderator
595 Views

Hi CLi37

we might need some time to further investigate this issue. please allow us some time to investigate it.


Thank you


0 Kudos
Hari_B_Intel
Moderator
568 Views

Hi CLi37,


Thank for your patience and understanding, we have two examples of OpenVINO EP for ONNX Runtime.

Jupyter notebook -> Reference_samples -> iot-devcloud -> openvino-lts -> developer-samples -> python -> ONNX-Object-detection-python

and

Jupyter notebook -> Reference_samples -> iot-devcloud -> openvino-lts -> developer-samples -> onnx_openvino_classification

 

Both can be used with Python3 (OpenVINO 2021.4.2) Kernel

 

For your information, DevCloud is not meant for training and I don't think there is possible to generate the model.

You can still upload the complete save model to DevCloud for prediction and distribution.


Hope this information helps


Thank you


0 Kudos
Reply