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.

Source Model for person-detection-retail-0013

Sandhu__Ranjit
Beginner
2,301 Views

Hi There,

 

I am looking for source mode "caffe" as mentioned in deployment_tools/intel_models/person-detection-retail-0013/description/person-detection-retail-0013.html. 

I have downloaded models using Model_downloader but it gives me  Retail\object_detection\pedestrian\rmnet_ssd\0013\dldt\person-detection-retail-0013-fp16.xml and  person-detection-retail-0013-fp16\bin files and not .cafee model file.

 

I want to use this model with model optimizer to customize its behaviour.

Thanks in advance.

~Ranjit

 

 

 

0 Kudos
17 Replies
Sandhu__Ranjit
Beginner
2,301 Views

Hi there ,

it looks like  the pre trained model used int for "person-detection-retail-0013" is  "rmnet_lrelu_pd_ssd.caffemodel" . So is it possible to get the model ?

Any help will be much appreciated

~Ranjit

0 Kudos
Sandhu__Ranjit
Beginner
2,301 Views

Hi Intel,

Please get me some direction on my question?

Regards,

Ranjit

 

0 Kudos
Dmitry_K_Intel3
Employee
2,301 Views

Check https://github.com/opencv/open_model_zoo/tree/2018/intel_models/person-detection-retail-0013. There is a Caffe's prototxt.

 

> I want to use this model with model optimizer to customize its behaviour.

 

Please clarify what indeed should be changed. Maybe it's possible without Model Optimizer.

0 Kudos
Sandhu__Ranjit
Beginner
2,301 Views

Hi Dmitry,

Thanks for answering my query. 

I want detection process to be really fast which will further  make tracking fast. For this to happen, I think if model be restricted to the  detection of persons having fixed size( probably bigger size) then all the persons which far away from the pedestrian crossing will not be detected as those appear to be of smaller in size as compare to actual people crossing the pedestrian.

So this way we have fewer detections/tracking which will ultimately improve its performance.

If you look at the current behaviour it do recognize the persons which are not really pedestrians and are far away from the pedestrain crossing but still it consider as pedestrians.

Appreciate any help and suggestions to make it fast.

Regards,

Ranjit

0 Kudos
Gdeep
Beginner
2,301 Views

hello sandhu saab,

Tusi pedestrian accuracy probability flag '-t' di value increase ker k deko, it will work fine   

0 Kudos
Sandhu__Ranjit
Beginner
2,301 Views

Thanks Gagan!

 

I tried but no luck.

~ranjit

0 Kudos
Gdeep
Beginner
2,301 Views

When try with your own data-set to train your custom model

 

0 Kudos
Sandhu__Ranjit
Beginner
2,301 Views

Sorry, could not get you. 

This is what I did as per your suggestion , I ran sample example of Pedestrian_tracker_demo example by setting -t to 100 as command line parameter and did not affect the outcome.

 

~ranjit

 

 

0 Kudos
Gdeep
Beginner
2,301 Views

first, you just check what the parameters we need to pass to run pedestrian_tracker_demo, I thing -t flag is not there, and the value of probability check flag should be float, not an integer, -t pass 0.90 

0 Kudos
Sandhu__Ranjit
Beginner
2,301 Views

Yep your are right 't' s not an option for this model but I tried as you suggested :). Surprisingly running a sample with wrong optional argument does not indicate any error about wrong argument.

Any other way to achieve the same thing ?

~ranjit 

0 Kudos
Sandhu__Ranjit
Beginner
2,301 Views

Nale veere apni bhasha vich nahi likh reha kyu mera hor colleagues vi mainu follow kar rahe ne is problem layee ise forum te  . Hope u understand :)

 

0 Kudos
Gdeep
Beginner
2,301 Views

see these are pre-trained samples so you can use these samples, and if you want more speed of inference then you can go with tiny yolo, 

and you from Punjab?

0 Kudos
Sandhu__Ranjit
Beginner
2,301 Views

Ok will spend some more time to your suggestions and will let you the results.

 

Yes, I am from Punjab but now settled in Australia.

~ranjit

0 Kudos
Gdeep
Beginner
2,301 Views

For the better understanding of your problem may I know what actually you want to do? 

0 Kudos
Sandhu__Ranjit
Beginner
2,301 Views

As mentioned earlier

"

I want detection process to be really fast which will further  make tracking fast. For this to happen, I think if model be restricted to the  detection of persons having fixed size( probably bigger size) then all the persons which far away from the pedestrian crossing will not be detected as those appear to be of smaller in size as compare to actual people crossing the pedestrian.

So this way we have fewer detections/tracking which will ultimately improve its performance.

If you look at the current behaviour it do recognize the persons which are not really pedestrians and are far away from the pedestrain crossing but still it consider as pedestrians."

So i want to use this model t0 count number of  people passed from one gate and keep tracking till they  go out of sight .

 

Ranjit

 

 

 

0 Kudos
Dmitry_K_Intel3
Employee
2,301 Views

If you look at the current behaviour it do recognize the persons which are not really pedestrians and are far away from the pedestrain crossing but still it consider as pedestrians.

 @Sandhu, Ranjit, Please provide some examples with images. And it's still a bit unclear for me, do you want to improve an accuracy of detections or efficiency of model (reduce inference time)?

0 Kudos
Mitra__Debasish
Beginner
2,301 Views

@Dmitry: I would like to access the cafee model file too so that I can benchmark and compare performance vs speed improvement for regular model vs optimized IR model.

0 Kudos
Reply