Steps to convert custom EfficientDet model from TensorFlow* 2 to IR
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'>)
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 support for TensorFlow* 2 Object Detection API has been enabled for OpenVINO™ Master Branch as per the following pull request.