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.
6392 Discussions

How do I get the format of the input and output of the trained model, for example, the graphical classification input is [1, 227

haiqing__zhang
Beginner
386 Views

 

I can only get the input and output names by executing     “python3 summarize_graph.py  --input_model  $tf_model”, and I want to get more detailed information about the output.

 

 

In addition,I want to get the input output of the following emotion recognition

 

Inputs

name: "input" , shape: [1x3x64x64] - An input image in [1xCxHxW] format. Expected color order is BGR.

Outputs

name: "prob", shape: [1, 5, 1, 1] - Softmax output across five emotions ('neutral', 'happy', 'sad', 'surprise', 'anger').

 

I would be grateful if you could give me good advice!

 

 

 

0 Kudos
2 Replies
haiqing__zhang
Beginner
386 Views

I want to get the output format of the output, for example the output of the classification is a vector,How to get information about this vector

0 Kudos
Shubha_R_Intel
Employee
386 Views

Dear haiqing, zhang,

What model are you interested in getting the input and output format for ?  Within OpenVino, all our samples show how to do that at run-time.  You can also find the dimensions of input and output in the generated IR.

If you need further help, please post here.

Thanks,

Shubha

 

0 Kudos
Reply