I had a pretrained model used in keas, for object detection i converted this model to IR format (model optimizer) , by passing from tenserflow. after that i loaded the model (xml, bin) in inference engine. the problem is that I dont have any information from the output glob returned after doing infer(). so i can not get the box of the detected object, using the same script in object detection samples I couldnt get nothing so what I have to do please
You may refer to this tutorial: https://www.youtube.com/watch?v=cbdS3BjjbaQ
Plus, please help to ensure that your model topology is listed here: https://docs.openvinotoolkit.org/latest/openvino_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_TensorFlow.html
If it's not, then it is not supported.
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.