Supported Model Formats

OpenVINO IR (Intermediate Representation) - the proprietary and default format of OpenVINO, benefiting from the full extent of its features. All other supported model formats, as listed below, are converted to OpenVINO IR to enable inference. Consider storing your model in this format to minimize first-inference latency, perform model optimization, and, in some cases, save space on your drive.

PyTorch, TensorFlow, ONNX, and PaddlePaddle - can be used with OpenVINO Runtime API directly, which means you do not need to save them as OpenVINO IR before including them in your application. OpenVINO can read, compile, and convert them automatically, as part of its pipeline.

In the Python API, these options are provided as three separate methods: read_model(), compile_model(), and convert_model(). The convert_model() method enables you to perform additional adjustments to the model, such as setting shapes, changing model input types or layouts, cutting parts of the model, freezing inputs, etc. For a detailed description of the conversion process, see the model conversion guide.

Here are code examples of how to use these methods with different model formats:

  • The convert_model() method:

    This is the only method applicable to PyTorch models.

    List of supported formats:

    • Python objects:

      • torch.nn.Module

      • torch.jit.ScriptModule

      • torch.jit.ScriptFunction

    model = torchvision.models.resnet50(pretrained=True)
ov_model = convert_model(model)
compiled_model = core.compile_model(ov_model, "AUTO")

    For more details on conversion, refer to the guide and an example tutorial on this topic.

  • The convert_model() method:

    When you use the convert_model() method, you have more control and you can specify additional adjustments for ov.Model. The read_model() and compile_model() methods are easier to use, however, they do not have such capabilities. With ov.Model you can choose to optimize, compile and run inference on it or serialize it into a file for subsequent use.

    List of supported formats:

    • Files:

      • SavedModel - <SAVED_MODEL_DIRECTORY> or <INPUT_MODEL>.pb

      • Checkpoint - <INFERENCE_GRAPH>.pb or <INFERENCE_GRAPH>.pbtxt

      • MetaGraph - <INPUT_META_GRAPH>.meta

    • Python objects:

      • tf.keras.Model

      • tf.keras.layers.Layer

      • tf.Module

      • tf.compat.v1.Graph

      • tf.compat.v1.GraphDef

      • tf.function

      • tf.compat.v1.session

      • tf.train.checkpoint

    ov_model = convert_model("saved_model.pb")
compiled_model = core.compile_model(ov_model, "AUTO")

    For more details on conversion, refer to the guide and an example tutorial on this topic.

  • The read_model() and compile_model() methods:

    List of supported formats:

    • Files:

      • SavedModel - <SAVED_MODEL_DIRECTORY> or <INPUT_MODEL>.pb

      • Checkpoint - <INFERENCE_GRAPH>.pb or <INFERENCE_GRAPH>.pbtxt

      • MetaGraph - <INPUT_META_GRAPH>.meta

    ov_model = read_model("saved_model.pb")
compiled_model = core.compile_model(ov_model, "AUTO")

    For a guide on how to run inference, see how to Integrate OpenVINO™ with Your Application. For TensorFlow format, see TensorFlow Frontend Capabilities and Limitations.

  • The compile_model() method:

    List of supported formats:

    • Files:

      • SavedModel - <SAVED_MODEL_DIRECTORY> or <INPUT_MODEL>.pb

      • Checkpoint - <INFERENCE_GRAPH>.pb or <INFERENCE_GRAPH>.pbtxt

      • MetaGraph - <INPUT_META_GRAPH>.meta

    ov::CompiledModel compiled_model = core.compile_model("saved_model.pb", "AUTO");

    For a guide on how to run inference, see how to Integrate OpenVINO™ with Your Application.

  • The compile_model() method:

    List of supported formats:

    • Files:

      • SavedModel - <SAVED_MODEL_DIRECTORY> or <INPUT_MODEL>.pb

      • Checkpoint - <INFERENCE_GRAPH>.pb or <INFERENCE_GRAPH>.pbtxt

      • MetaGraph - <INPUT_META_GRAPH>.meta

    ov_compiled_model_t* compiled_model = NULL;
ov_core_compile_model_from_file(core, "saved_model.pb", "AUTO", 0, &compiled_model);

    For a guide on how to run inference, see how to Integrate OpenVINO™ with Your Application.

You can use mo command-line tool to convert a model to IR. The obtained IR can then be read by read_model() and inferred.

mo --input_model <INPUT_MODEL>.pb

For details on the conversion, refer to the article.

  • The convert_model() method:

    When you use the convert_model() method, you have more control and you can specify additional adjustments for ov.Model. The read_model() and compile_model() methods are easier to use, however, they do not have such capabilities. With ov.Model you can choose to optimize, compile and run inference on it or serialize it into a file for subsequent use.

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.tflite

    ov_model = convert_model("<INPUT_MODEL>.tflite")
compiled_model = core.compile_model(ov_model, "AUTO")

    For more details on conversion, refer to the guide and an example tutorial on this topic.

  • The read_model() method:

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.tflite

    ov_model = read_model("<INPUT_MODEL>.tflite")
compiled_model = core.compile_model(ov_model, "AUTO")

  • The compile_model() method:

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.tflite

    compiled_model = core.compile_model("<INPUT_MODEL>.tflite", "AUTO")

    For a guide on how to run inference, see how to Integrate OpenVINO™ with Your Application.

  • The compile_model() method:

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.tflite

    ov::CompiledModel compiled_model = core.compile_model("<INPUT_MODEL>.tflite", "AUTO");

    For a guide on how to run inference, see how to Integrate OpenVINO™ with Your Application.

  • The compile_model() method:

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.tflite

    ov_compiled_model_t* compiled_model = NULL;
ov_core_compile_model_from_file(core, "<INPUT_MODEL>.tflite", "AUTO", 0, &compiled_model);

    For a guide on how to run inference, see how to Integrate OpenVINO™ with Your Application.

  • The convert_model() method:

    You can use mo command-line tool to convert a model to IR. The obtained IR can then be read by read_model() and inferred.

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.tflite

    mo --input_model <INPUT_MODEL>.tflite

    For details on the conversion, refer to the article.

  • The convert_model() method:

    When you use the convert_model() method, you have more control and you can specify additional adjustments for ov.Model. The read_model() and compile_model() methods are easier to use, however, they do not have such capabilities. With ov.Model you can choose to optimize, compile and run inference on it or serialize it into a file for subsequent use.

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.onnx

    ov_model = convert_model("<INPUT_MODEL>.onnx")
compiled_model = core.compile_model(ov_model, "AUTO")

    For more details on conversion, refer to the guide and an example tutorial on this topic.

  • The read_model() method:

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.onnx

    ov_model = read_model("<INPUT_MODEL>.onnx")
compiled_model = core.compile_model(ov_model, "AUTO")

  • The compile_model() method:

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.onnx

    compiled_model = core.compile_model("<INPUT_MODEL>.onnx", "AUTO")

    For a guide on how to run inference, see how to Integrate OpenVINO™ with Your Application.

  • The compile_model() method:

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.onnx

    ov::CompiledModel compiled_model = core.compile_model("<INPUT_MODEL>.onnx", "AUTO");

    For a guide on how to run inference, see how to Integrate OpenVINO™ with Your Application.

  • The compile_model() method:

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.onnx

    ov_compiled_model_t* compiled_model = NULL;
ov_core_compile_model_from_file(core, "<INPUT_MODEL>.onnx", "AUTO", 0, &compiled_model);

    For details on the conversion, refer to the article

  • The convert_model() method:

    You can use mo command-line tool to convert a model to IR. The obtained IR can then be read by read_model() and inferred.

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.onnx

    mo --input_model <INPUT_MODEL>.onnx

    For details on the conversion, refer to the article

  • The convert_model() method:

    When you use the convert_model() method, you have more control and you can specify additional adjustments for ov.Model. The read_model() and compile_model() methods are easier to use, however, they do not have such capabilities. With ov.Model you can choose to optimize, compile and run inference on it or serialize it into a file for subsequent use.

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.pdmodel

    • Python objects:

      • paddle.hapi.model.Model

      • paddle.fluid.dygraph.layers.Layer

      • paddle.fluid.executor.Executor

    ov_model = convert_model("<INPUT_MODEL>.pdmodel")
compiled_model = core.compile_model(ov_model, "AUTO")

    For more details on conversion, refer to the guide and an example tutorial on this topic.

  • The read_model() method:

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.pdmodel

    ov_model = read_model("<INPUT_MODEL>.pdmodel")
compiled_model = core.compile_model(ov_model, "AUTO")

  • The compile_model() method:

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.pdmodel

    compiled_model = core.compile_model("<INPUT_MODEL>.pdmodel", "AUTO")

    For a guide on how to run inference, see how to Integrate OpenVINO™ with Your Application.

  • The compile_model() method:

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.pdmodel

    ov::CompiledModel compiled_model = core.compile_model("<INPUT_MODEL>.pdmodel", "AUTO");

    For a guide on how to run inference, see how to Integrate OpenVINO™ with Your Application.

  • The compile_model() method:

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.pdmodel

    ov_compiled_model_t* compiled_model = NULL;
ov_core_compile_model_from_file(core, "<INPUT_MODEL>.pdmodel", "AUTO", 0, &compiled_model);

    For a guide on how to run inference, see how to Integrate OpenVINO™ with Your Application.

  • The convert_model() method:

    You can use mo command-line tool to convert a model to IR. The obtained IR can then be read by read_model() and inferred.

    List of supported formats:

    • Files:

      • <INPUT_MODEL>.pdmodel

    mo --input_model <INPUT_MODEL>.pdmodel

    For details on the conversion, refer to the article.

MXNet, Caffe, and Kaldi are legacy formats that need to be converted explicitly to OpenVINO IR or ONNX before running inference. As OpenVINO is currently proceeding to deprecate these formats and remove their support entirely in the future, converting them to ONNX for use with OpenVINO should be considered the default path.

Note

If you want to keep working with the legacy formats the old way, refer to a previous OpenVINO LTS version and its documentation .

OpenVINO versions of 2023 are mostly compatible with the old instructions, through a deprecated MO tool, installed with the deprecated OpenVINO Developer Tools package.

OpenVINO 2023.0 is the last release officially supporting the MO conversion process for the legacy formats.