Article ID: 000095016 Content Type: Troubleshooting Last Reviewed: 05/30/2023

Unable to Convert Custom Trained TensorFlow* Model Using Model Optimizer

BUILT IN - ARTICLE INTRO SECOND COMPONENT
Summary

How to convert custom trained TensorFlow* model to Intermediate Representation (IR) format in Model Optimizer.

Description

Ran the following command:

mo --saved_model_dir saved_model_0/

Encountered error:

[ ERROR ] Exception occurred during running replacer "REPLACEMENT_ID" (<class 'openvino.tools.mo.middle.PartialInfer.PartialInfer'>): Stopped shape/value propagation at "ParseExample/ParseExampleV2" node.
For more information please refer to Model Optimizer FAQ, question #38. (https://docs.openvino.ai/latest/openvino_docs_MO_DG_prepare_model_Model_Optimizer_FAQ.html?question=38#question-38)
[ INFO ] You can also try to use new TensorFlow Frontend (preview feature as of 2022.3) by adding `--use_new_frontend` option into Model Optimizer command-line.
Find more information about new TensorFlow Frontend at https://docs.openvino.ai/latest/openvino_docs_MO_DG_TensorFlow_Frontend.html

Resolution

Convert the custom trained TensorFlow model by specifying the following parameters in Model Optimizer:

--input, --output, --input_shape, --reverse_input_channels

Refer Model Optimizer Usage guide for more information in converting models into IR format.

Related Products

This article applies to 1 products