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.
5532 Discussions

TensorFlow Model Inference Issue with Interpolate operation

ibrahimsoliman
Beginner
162 Views

Hi,

I am using OpenVINO 2021.2 on Windows 10. 

I am facing the below issue during inference:

Interpolate operation should be converted to Interp 

My original model is TensorFlow PB, I can convert the model using model optimizer without any problem.
Model inference will run successfully if NHWC to NCHW is enabled. but if I disabled this channel conversion, Inference will fail.

Success command:

python mo_tf.py --input_model ./model.pb --input input_3 --output conv2d_72/Sigmoid --input_shape [1,256,256,1]

 Infernce Fail Command:

python mo_tf.py --input_model ./model.pb --input input_3 --output conv2d_72/Sigmoid --input_shape [1,256,256,1] --disable_nhwc_to_nchw

"Both conversion commands, Model Optimizer runs correctly and produce IR". but when I add `--disable_nhwc_to_nchw` (command 2) I will not be able to infer correctly and I will get following error: `Interpolate operation should be converted to Interp `.

Thanks

 

0 Kudos
2 Replies
Iffa_Intel
Moderator
136 Views

Greetings,


The reason for this is that Tensorflow is the only network out there that uses NHWC. All other networks use NCHW. Thus OpenVino's Inference Engine satisfies the majority so it also uses NCHW layout. Models of all network flavors must be converted to NCHW layout in order to work with Inference Engine.


Sincerely,

Iffa


Iffa_Intel
Moderator
124 Views

Greetings,


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


Sincerely,

Iffa


Reply