Article ID: 000059778 Content Type: Error Messages Last Reviewed: 08/05/2022

Unable to Convert Custom EfficientDet Model from TensorFlow* 2 to Intermediate Representation (IR)

Environment

OpenVINO 2021.3

BUILT IN - ARTICLE INTRO SECOND COMPONENT
Summary

Steps to convert custom EfficientDet model from TensorFlow* 2 to IR

Description

Encountered error when converting custom EfficientDet model from TensorFlow* 2 to IR:

[ ERROR ] Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.load.tf.loader.TFLoader'>)

Resolution

Execute the Model Optimizer conversion command in OpenVINO™ 2021.4:

python mo.py --saved_model_dir "<path_to_saved_model_dir>" --tensorflow_object_detection_api_pipeline_config "<path_to_pipeline_config>\pipeline.config" --transformations_config "<INSTALL_DIR>\model-optimizer\extensions\front\tf\ssd_support_api_v2.4.json"

Additional information

Additional support for TensorFlow* 2 Object Detection API has been enabled for OpenVINO™ Master Branch as per the following pull request.

Related Products

This article applies to 1 products