Model Optimizer Developer Guide — OpenVINO™ documentation

Introduction¶

Model Optimizer is a cross-platform command-line tool that facilitates the transition between the training and deployment environment, performs static model analysis, and adjusts deep learning models for optimal execution on end-point target devices.

Model Optimizer process assumes you have a network model trained using supported deep learning frameworks: Caffe*, TensorFlow*, Kaldi*, MXNet* or converted to the ONNX* format. Model Optimizer produces an Intermediate Representation (IR) of the network, which can be inferred with the Inference Engine.

Note

Model Optimizer does not infer models. Model Optimizer is an offline tool that runs before the inference takes place.

The scheme below illustrates the typical workflow for deploying a trained deep learning model:

The IR is a pair of files describing the model:

.xml - Describes the network topology
.bin - Contains the weights and biases binary data.

Tip

You also can work with the Model Optimizer inside the OpenVINO™ Deep Learning Workbench (DL Workbench). DL Workbench is a web-based graphical environment that enables you to optimize, fine-tune, analyze, visualize, and compare performance of deep learning models.

Install Model Optimizer Pre-Requisites¶

Before running the Model Optimizer, you must install the Model Optimizer pre-requisites for the framework that was used to train the model.

Using configuration scripts

Using manual configuration process

Run Model Optimizer¶

To convert the model to the Intermediate Representation (IR), run Model Optimizer using the command for your type of OpenVINO™ installation:

Package, Docker, open-source installation

python3 <INSTALL_DIR>/deployment_tools/model_optimizer/mo.py --input_model INPUT_MODEL --output_dir <OUTPUT_MODEL_DIR>

pip installation

mo --input_model INPUT_MODEL --output_dir <OUTPUT_MODEL_DIR>

You need to have have write permissions for an output directory.

Note

Some models require using additional arguments to specify conversion parameters, such as --input_shape, --scale, --scale_values, --mean_values, --mean_file. To learn about when you need to use these parameters, refer to Converting a Model to Intermediate Representation (IR).

To adjust the conversion process, you may use general parameters defined in the Converting a Model to Intermediate Representation (IR) and framework-specific parameters for:

Caffe
TensorFlow
MXNet
ONNX
Kaldi

Videos¶


Model Optimizer Concept.	Model Optimizer Basic Operation.	Choosing the Right Precision.
Duration: 3:56	Duration: 2:57	Duration: 4:18

Model Optimizer Developer Guide¶

Introduction¶

Install Model Optimizer Pre-Requisites¶

Run Model Optimizer¶

Videos¶