Error while converting saved_model (tensorflow 1.14) model

[TarunMishra]

I am getting the following error while converting the model:-

[ ERROR ] 'ascii' codec can't decode byte 0xd9 in position 1: ordinal not in range(128)
Unexpected exception happened during extracting attributes for node training/Adam/dense/bias/v/Read/ReadVariableOp.
Original exception message: 'ascii' codec can't decode byte 0xd9 in position 1: ordinal not in range(128)

I am attaching the folder after zipping (gender.zip). I ran the following command:-

python mo.py --saved_model_dir "./gender"

I am also attaching the tensorflow 1.14 code used to create the saved model (train.zip)

[Munesh_Intel]

Hi Tarun,

Please share more information about your model, is it an object detection/classification model, if custom model what type of layers does the model use, and environment details (versions of OpenVINO, OS, Python, CMake, etc.).

Regards,

Munesh.

[Munesh_Intel · Accepted solution]

Hi Tarun,

The error 'ascii codec can't decode byte' generally occurs when you convert a Python 2.x str that contains non-ASCII to a Unicode string without specifying the encoding of the original string.

For your further information, do have a look at the following thread, which involves similar issue as you are facing.

https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Original-exception-message-ascii-codec-can-t-decode-byte-0xee-in/td-p/1190202

Regards,

Munesh

[Munesh_Intel]

Hi Tarun,

This thread will no longer be monitored since we have provided a solution. If you need any additional information from Intel, please submit a new question.

Regards,

Munesh