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.
6426 Discussions

Error while converting custom trained MaskRCnn Tensorflow 2.0 model

Vicenc
Novice
1,932 Views

Hello, I am trying to convert a retrained TF OD API Mask RCNN model, which works on GPU, but I am not able to use 'mo' since it's giving me errore:

 

The command I use is:

mo \
> --saved_model_dir '<DIR_TF_model>/Tensorflow-Object-Detection-API-train-custom-Mask-R-CNN-model-master/inference_graph/saved_model' \
> --transformations_config '<DIR_OV>/openvino_env/lib/python3.7/site-packages/openvino/tools/mo/front/tf/mask_rcnn_support_api_v2.0.json' \
> --tensorflow_object_detection_api_pipeline_config '<DIR_TF>/Tensorflow-Object-Detection-API-train-custom-Mask-R-CNN-model-master/inference_graph/pipeline.config' \
> --reverse_input_channels

 

TF Version is 2.4

 

The error is:

[ ERROR ] -------------------------------------------------
[ ERROR ] ----------------- INTERNAL ERROR ----------------
[ ERROR ] Unexpected exception happened.
[ ERROR ] Please contact Model Optimizer developers and forward the following information:
[ ERROR ] Exception occurred during running replacer "ObjectDetectionAPIPreprocessor2Replacement (<class 'openvino.tools.mo.front.tf.ObjectDetectionAPI.ObjectDetectionAPIPreprocessor2Replacement'>)

 

I would appreciate very much any help to solve this issue,

 

Vicenç

 

 

 

1 Solution
Iffa_Intel
Moderator
1,707 Views

I checked your model and managed to convert it. (Note that your model is dynamic shaped)

This is the command that I used: mo --saved_model_dir "C:\Users\sjaismex\Downloads\saved_model (1)\saved_model"

The best is to provide your input shape together here, eg: mo --saved_model_dir "C:\Users\sjaismex\Downloads\saved_model (1)\saved_model" --input_shape [1, -1, -1, 3]

Iffa_Intel_0-1681781754241.png

 

 

This is the inferencing result for your model.

Command that I used: benchmark_app -m C:\Users\sjaismex\saved_model.xml -data_shape [1,5,4,3]

 

Iffa_Intel_1-1681789506742.png

 

 

Cordially,

Iffa

 

View solution in original post

0 Kudos
11 Replies
Iffa_Intel
Moderator
1,910 Views

Hi,


could you share the relevant files for us to validate? (model files, etc)



Cordially,

Iffa


0 Kudos
Vicenc
Novice
1,895 Views

Hi Iffa, yes, of course.

 

The relevant files are attached now, please tell me if you need additional files or information.

 

* The versions of OpenVino and TensorFlow are:

 

tensorflow==2.4.0

openvino==2022.3.0

 

Thank you very much,

 

Vicenç Parisi

 

 

0 Kudos
Iffa_Intel
Moderator
1,873 Views

Your saved_model files that were shared are incomplete.

The SavedModel format should consist of a directory with a saved_model.pb file and two subfolders: variables and assets.


Make sure you are using & sharing the correct Tensorflow model file


Cordially,

Iffa



0 Kudos
Vicenc
Novice
1,853 Views

Hi, thank you for your message.

 

I know that they are incomplete, but the folder size is 222MB and cannot be attached.

("The file (saved_model.tar.xz) exceeds the maximum file size. The maximum file size is 71 MB.")

I would appreciate very much if you can give me advice on how to send it.

 

Vicenç

0 Kudos
Iffa_Intel
Moderator
1,837 Views

You could upload it to Google Drive & share the link with me (I'll request access afterward if you made this file private) or upload it to your GitHub page.

I don't think sharing through my Intel email is an option here since this also has a limit for file size.


Cordially,

Iffa


0 Kudos
Vicenc
Novice
1,795 Views

Hi Iffa,

 

  the link to the saved_model compressed folder is:

 

https://drive.google.com/file/d/1hyL5bjGp6V5bUpjCplQFoMTkyUN4QuX7/view?usp=share_link

 

Thank you!

 

Vicenç 

0 Kudos
Iffa_Intel
Moderator
1,739 Views

I had requested access.

 

Iffa_Intel_0-1681691340655.png

 

Cordially,

Iffa

0 Kudos
Iffa_Intel
Moderator
1,708 Views

I checked your model and managed to convert it. (Note that your model is dynamic shaped)

This is the command that I used: mo --saved_model_dir "C:\Users\sjaismex\Downloads\saved_model (1)\saved_model"

The best is to provide your input shape together here, eg: mo --saved_model_dir "C:\Users\sjaismex\Downloads\saved_model (1)\saved_model" --input_shape [1, -1, -1, 3]

Iffa_Intel_0-1681781754241.png

 

 

This is the inferencing result for your model.

Command that I used: benchmark_app -m C:\Users\sjaismex\saved_model.xml -data_shape [1,5,4,3]

 

Iffa_Intel_1-1681789506742.png

 

 

Cordially,

Iffa

 

0 Kudos
Vicenc
Novice
1,674 Views

Thank you very much Iffa!!!

 

So, we don't need to specify transformations_config and tensorflow_object_detection_api_pipeline_config?

 

By the way, which CPU did you use to do the inference test (it it an i7?) , I am asking this because the inference time is around 60s per image? 

 

Is there a way to make it faster?

 

Cordially,

 

Vicenç

 

0 Kudos
Iffa_Intel
Moderator
1,656 Views

You might want to pay attention to the Warnings that prompted.

They didn't cause errors but they might help your model to function more efficiently.

 

Yes I'm using i7 for the testing. You can consider using OpenVINO Model Optimization to improve the performance.

 

Cordially,

Iffa

 

0 Kudos
Iffa_Intel
Moderator
1,548 Views

Hi,


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. 


Cordially,

Iffa


0 Kudos
Reply