Community
cancel
Showing results for 
Search instead for 
Did you mean: 
Karan
Novice
269 Views

Access denied

I save my .h5 model using 
tf.saved_model.save(model,'model')
now when I try to use the model optimizer im getting access denie error
Karan_0-1595341404201.png

 

0 Kudos
6 Replies
Iffa_Intel
Moderator
248 Views

Greetings,


Your problem seems to originate from directories access.

I believe you are running this code with Anaconda.

As a workaround, try to run the Anaconda cmd as admin & run jupyter notebook in it.

Then, try to see whether this conflict still persist.


Btw, you need to fill in the --saved_model_dir <location of your saved model> and --input_shape <write your input shape>



Sincerely,

Iffa


Karan
Novice
232 Views

@Iffa_Intel 

I did try running the command from the terminal as admin as well still getting the same error, decided to do this on the intel dev cloud, this time i was able open the directory but this is what i got

Karan_0-1595505643976.png

My tensor flow saved model directory name is 'model' hence I pass model to --saved_model_dir

Iffa_Intel
Moderator
222 Views

I used the command that can be found in OpenVino Official Documentation:

https://docs.openvinotoolkit.org/latest/openvino_docs_MO_DG_prepare_model_convert_model_tf_specific_...

 

This is what i get:

Convert yolo to IR

python mo_tf.py --input_model C:\Users \Desktop\OpenVINO-Experiments\Yolov3\tensorflow-yolo-v3\frozen_darknet_yolov3_model.pb --tensorflow_use_custom_operations_config C:\Users \Desktop\OpenVINO-Experiments\Yolov3\yolo_v3.json --batch 1

 

Iffa_Intel_0-1595562654973.jpeg

 

 

And I'm able to Run object_detection_demo_yolov3_async.py

python object_detection_demo_yolov3_async.py -i inputVideo.mp4 -m frozen_darknet_yolov3_model.xml -d CPU

 

Iffa_Intel_1-1595562654984.jpeg

Perhaps you can do the same by referring to the official documentation

This is a video that might help you: https://www.youtube.com/watch?v=FaqVhvJ6-Uc

 

Sincerely,

Iffa

Karan
Novice
214 Views

I am using tensorflow 2.2, therefore my model is in SavedModel format which consists of a directory with a saved_model.pb file and two subfolders: variables and assets.

According to the documentation i am requred to give this command

python3 mo_tf.py --saved_model_dir <SAVED_MODEL_DIRECTORY>

I have successfully run the command but im getting this error 

 
Karan
Novice
208 Views

@Iffa_Intel 

Okay found a solution, rather the reason that was causing the problem.

So the thing is I was using openVINO 2020.3 toolkit this whole time. 
I have upgraded to openVINO 2020.4 and now all the problems have gone. 

If anyone is facing this issue I hope this helps.

Iffa_Intel
Moderator
198 Views

Glad to hear that!


Sincerely,

Iffa


Reply