mlflow.onnx

The mlflow.onnx module provides APIs for logging and loading ONNX models in the MLflow Model format. This module exports MLflow Models with the following flavors:

ONNX (native) format

This is the main flavor that can be loaded back as an ONNX model object.

mlflow.pyfunc

Produced for use by generic pyfunc-based deployment tools and batch inference.

mlflow.onnx.get_default_conda_env()[source]

Note

Experimental: This method may change or be removed in a future release without warning.

Returns

The default Conda environment for MLflow Models produced by calls to save_model() and log_model().

mlflow.onnx.get_default_pip_requirements()[source]
Returns

A list of default pip requirements for MLflow Models produced by this flavor. Calls to save_model() and log_model() produce a pip environment that, at minimum, contains these requirements.

mlflow.onnx.load_model(model_uri, dst_path=None)[source]

Note

Experimental: This method may change or be removed in a future release without warning.

Load an ONNX model from a local file or a run.

Parameters
  • model_uri

    The location, in URI format, of the MLflow model, for example:

    • /Users/me/path/to/local/model

    • relative/path/to/local/model

    • s3://my_bucket/path/to/model

    • runs:/<mlflow_run_id>/run-relative/path/to/model

    • models:/<model_name>/<model_version>

    • models:/<model_name>/<stage>

    For more information about supported URI schemes, see the Artifacts Documentation.

  • dst_path – The local filesystem path to which to download the model artifact. This directory must already exist. If unspecified, a local output path will be created.

Returns

An ONNX model instance.

mlflow.onnx.log_model(onnx_model, artifact_path, conda_env=None, code_paths=None, registered_model_name=None, signature: mlflow.models.signature.ModelSignature = None, input_example: Union[pandas.core.frame.DataFrame, numpy.ndarray, dict, list, csr_matrix, csc_matrix] = None, await_registration_for=300, pip_requirements=None, extra_pip_requirements=None, onnx_execution_providers=None)[source]

Note

Experimental: This method may change or be removed in a future release without warning.

Log an ONNX model as an MLflow artifact for the current run.

Parameters
  • onnx_model – ONNX model to be saved.

  • artifact_path – Run-relative artifact path.

  • conda_env

    Either a dictionary representation of a Conda environment or the path to a conda environment yaml file. If provided, this describes the environment this model should be run in. At minimum, it should specify the dependencies contained in get_default_conda_env(). If None, a conda environment with pip requirements inferred by mlflow.models.infer_pip_requirements() is added to the model. If the requirement inference fails, it falls back to using get_default_pip_requirements(). pip requirements from conda_env are written to a pip requirements.txt file and the full conda environment is written to conda.yaml. The following is an example dictionary representation of a conda environment:

    {
        "name": "mlflow-env",
        "channels": ["conda-forge"],
        "dependencies": [
            "python=3.7.0",
            {
                "pip": [
                    "onnx==x.y.z"
                ],
            },
        ],
    }
    

  • code_paths – A list of local filesystem paths to Python file dependencies (or directories containing file dependencies). These files are prepended to the system path when the model is loaded.

  • registered_model_name – If given, create a model version under registered_model_name, also creating a registered model if one with the given name does not exist.

  • signature

    ModelSignature describes model input and output Schema. The model signature can be inferred from datasets with valid model input (e.g. the training dataset with target column omitted) and valid model output (e.g. model predictions generated on the training dataset), for example:

    from mlflow.models.signature import infer_signature
    train = df.drop_column("target_label")
    predictions = ... # compute model predictions
    signature = infer_signature(train, predictions)
    

  • input_example – Input example provides one or several instances of valid model input. The example can be used as a hint of what data to feed the model. The given example can be a Pandas DataFrame where the given example will be serialized to json using the Pandas split-oriented format, or a numpy array where the example will be serialized to json by converting it to a list. Bytes are base64-encoded.

  • await_registration_for – Number of seconds to wait for the model version to finish being created and is in READY status. By default, the function waits for five minutes. Specify 0 or None to skip waiting.

  • pip_requirements – Either an iterable of pip requirement strings (e.g. ["onnx", "-r requirements.txt", "-c constraints.txt"]) or the string path to a pip requirements file on the local filesystem (e.g. "requirements.txt"). If provided, this describes the environment this model should be run in. If None, a default list of requirements is inferred by mlflow.models.infer_pip_requirements() from the current software environment. If the requirement inference fails, it falls back to using get_default_pip_requirements(). Both requirements and constraints are automatically parsed and written to requirements.txt and constraints.txt files, respectively, and stored as part of the model. Requirements are also written to the pip section of the model’s conda environment (conda.yaml) file.

  • extra_pip_requirements

    Either an iterable of pip requirement strings (e.g. ["pandas", "-r requirements.txt", "-c constraints.txt"]) or the string path to a pip requirements file on the local filesystem (e.g. "requirements.txt"). If provided, this describes additional pip requirements that are appended to a default set of pip requirements generated automatically based on the user’s current software environment. Both requirements and constraints are automatically parsed and written to requirements.txt and constraints.txt files, respectively, and stored as part of the model. Requirements are also written to the pip section of the model’s conda environment (conda.yaml) file.

    Warning

    The following arguments can’t be specified at the same time:

    • conda_env

    • pip_requirements

    • extra_pip_requirements

    This example demonstrates how to specify pip requirements using pip_requirements and extra_pip_requirements.

  • onnx_execution_providers – List of strings defining onnxruntime execution providers. Defaults to example: [‘CUDAExecutionProvider’, ‘CPUExecutionProvider’] This uses GPU preferentially over CPU. See onnxruntime API for further descriptions: https://onnxruntime.ai/docs/execution-providers/

Returns

A ModelInfo instance that contains the metadata of the logged model.

mlflow.onnx.save_model(onnx_model, path, conda_env=None, code_paths=None, mlflow_model=None, signature: mlflow.models.signature.ModelSignature = None, input_example: Union[pandas.core.frame.DataFrame, numpy.ndarray, dict, list, csr_matrix, csc_matrix] = None, pip_requirements=None, extra_pip_requirements=None, onnx_execution_providers=None)[source]

Note

Experimental: This method may change or be removed in a future release without warning.

Save an ONNX model to a path on the local file system.

Parameters
  • onnx_model – ONNX model to be saved.

  • path – Local path where the model is to be saved.

  • conda_env

    Either a dictionary representation of a Conda environment or the path to a conda environment yaml file. If provided, this describes the environment this model should be run in. At minimum, it should specify the dependencies contained in get_default_conda_env(). If None, a conda environment with pip requirements inferred by mlflow.models.infer_pip_requirements() is added to the model. If the requirement inference fails, it falls back to using get_default_pip_requirements(). pip requirements from conda_env are written to a pip requirements.txt file and the full conda environment is written to conda.yaml. The following is an example dictionary representation of a conda environment:

    {
        "name": "mlflow-env",
        "channels": ["conda-forge"],
        "dependencies": [
            "python=3.7.0",
            {
                "pip": [
                    "onnx==x.y.z"
                ],
            },
        ],
    }
    

  • code_paths – A list of local filesystem paths to Python file dependencies (or directories containing file dependencies). These files are prepended to the system path when the model is loaded.

  • mlflow_modelmlflow.models.Model this flavor is being added to.

  • signature

    ModelSignature describes model input and output Schema. The model signature can be inferred from datasets with valid model input (e.g. the training dataset with target column omitted) and valid model output (e.g. model predictions generated on the training dataset), for example:

    from mlflow.models.signature import infer_signature
    train = df.drop_column("target_label")
    predictions = ... # compute model predictions
    signature = infer_signature(train, predictions)
    

  • input_example – Input example provides one or several instances of valid model input. The example can be used as a hint of what data to feed the model. The given example can be a Pandas DataFrame where the given example will be serialized to json using the Pandas split-oriented format, or a numpy array where the example will be serialized to json by converting it to a list. Bytes are base64-encoded.

  • pip_requirements – Either an iterable of pip requirement strings (e.g. ["onnx", "-r requirements.txt", "-c constraints.txt"]) or the string path to a pip requirements file on the local filesystem (e.g. "requirements.txt"). If provided, this describes the environment this model should be run in. If None, a default list of requirements is inferred by mlflow.models.infer_pip_requirements() from the current software environment. If the requirement inference fails, it falls back to using get_default_pip_requirements(). Both requirements and constraints are automatically parsed and written to requirements.txt and constraints.txt files, respectively, and stored as part of the model. Requirements are also written to the pip section of the model’s conda environment (conda.yaml) file.

  • extra_pip_requirements

    Either an iterable of pip requirement strings (e.g. ["pandas", "-r requirements.txt", "-c constraints.txt"]) or the string path to a pip requirements file on the local filesystem (e.g. "requirements.txt"). If provided, this describes additional pip requirements that are appended to a default set of pip requirements generated automatically based on the user’s current software environment. Both requirements and constraints are automatically parsed and written to requirements.txt and constraints.txt files, respectively, and stored as part of the model. Requirements are also written to the pip section of the model’s conda environment (conda.yaml) file.

    Warning

    The following arguments can’t be specified at the same time:

    • conda_env

    • pip_requirements

    • extra_pip_requirements

    This example demonstrates how to specify pip requirements using pip_requirements and extra_pip_requirements.

  • onnx_execution_providers – List of strings defining onnxruntime execution providers. Defaults to example: ['CUDAExecutionProvider', 'CPUExecutionProvider'] This uses GPU preferentially over CPU. See onnxruntime API for further descriptions: https://onnxruntime.ai/docs/execution-providers/