DNN network architecture of the original parent network from which the Intel OpenVINO pre-trained models were optimized and if yes, how?

Question

I have used pre-trained models from OpenVINO for inference. I would like to know how to see the network structure of these models? And if I want to re-train these networks from scratch, can I know from which parent models these pre-trained models were originally derived from?

Answer 1

• Information about Intel pre-trained models is available at the following page, “Overview of OpenVINO™ Toolkit Intel's Pre-Trained Models”. https://docs.openvinotoolkit.org/2020.4/omz_models_intel_index.html

• Information about public pre-trained models is available at the following page, “Overview of OpenVINO™ Toolkit Public Models”. https://docs.openvinotoolkit.org/2020.4/omz_models_public_index.html

• DL Workbench can be used to visualize the network structure. DL Workbench is a web-based graphical environment that enables users to visualize, fine-tune, and compare performance of deep learning models. More information about DL Workbench is available at the following page, “Introduction to Deep Learning Workbench”. https://docs.openvinotoolkit.org/2020.4/workbench_docs_Workbench_DG_Introduction.html