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

[security_barrier_camera_demo] RGB data handling for LPR model

LEE__JS
Beginner
294 Views

Dear Sir or Madam,

 

I am trying to Change the LPR model from the default model to the model I have trained.

But the issue is that RGB value of the input image should be divided by 255.

 

Please help me.

 

Sincerely,

JS 

0 Kudos
3 Replies
JesusE_Intel
Moderator
294 Views

Hi LEE, JS,

Did you convert your model using the --reverse_input_channels flag on the Model Optimizer?

Regards,

Jesus

0 Kudos
LEE__JS
Beginner
294 Views

Dear Jesus E. (Intel),

Thank you for your comment.

My concern was that is their any possible way to lower the value of RGB instead of making RGB to BGR.

Sincerely,
JS
 

0 Kudos
JesusE_Intel
Moderator
294 Views

Hi JS,

I apologize, I misunderstood your question. You should be able to use the --scale parameter as mentioned in the Model Optimizer documentation.

 --scale SCALE, -s SCALE
                        All input values coming from original network inputs
                        will be divided by this value. When a list of inputs
                        is overridden by the --input parameter, this scale is
                        not applied for any input that does not match with the
                        original input of the model.

Please let me know if this is what you are looking for.

Regards,

Jesus

0 Kudos
Reply