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

OpenVino support variable Input image, but results are different

TonyWong
Beginner
458 Views

Dear Intel Guru,

 

Hi, I have tried OpenVino, and it is awesome.

 

I'm having another question.

My input model size is [1,3, height, width]

I just tried, and it seems it does support variable input size. 

 

However: 

Using the mo.py,  though the warming still mentioned that it is still strongly suggested to use static input size.

 

The results are different with original ONNX format. 

Anyone can help?

Here is the  model link:

 

and the command  is :

$python mo.py --input_model model.onnx --output_dir ~/Downloads

 

 

Tony

 

0 Kudos
3 Replies
TonyWong
Beginner
448 Views

The key is: results are different.

 

Even the dimension   

from 48*80*606

to: 30*40*606

0 Kudos
Iffa_Intel
Moderator
422 Views

Hi @TonyWong ,

 

From the Model Optimizer, you can feed the input shape by using --input_shape parameter.

Example:  python mo.py --input_model model.onnx --output_dir ~/Downloads --input_shape [1,3,227,227]

 

Note that the order of dimension depends on the framework input layout of the model.

For instance:

1. Caffe model: [N,C,H,W]

2. Tensorflow model: [N,H,W,C]

 

Model Optimizer requires [N,C,H,W] layout and would perform the necessary transformation to the model. The shape should not contain undefined dimensions such as (? or -1).

 

Depending on your model, you need to consider these:

1. When to specify input shape

2. When to reverse input channel

 

Hope this helps!

Sincerely,

Iffa

 

 

0 Kudos
Iffa_Intel
Moderator
398 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


0 Kudos
Reply