Skip to content

PySDK Package

degirum.LOCAL: str = ZooManager._LOCAL module-attribute

Local inference designator: use it as a first argument of degirum.connect function to specify inference on local AI hardware

degirum.CLOUD: str = ZooManager._CLOUD module-attribute

Cloud inference designator: use it as a first argument of degirum.connect function to specify cloud-based inference

degirum.connect(inference_host_address, zoo_url=None, token=None)

Connect to the AI inference host and model zoo of your choice.

This is the main PySDK entry point: you start your work with PySDK by calling this function.

The following use cases are supported:

  1. You want to perform cloud inferences and take models from some cloud model zoo.
  2. You want to perform inferences on some AI server and take models from some cloud model zoo.
  3. You want to perform inferences on some AI server and take models from its local model zoo.
  4. You want to perform inferences on local AI hardware and take models from some cloud model zoo.
  5. You want to perform inferences on local AI hardware and take models from the local model zoo directory on your local drive.
  6. You want to perform inferences on local AI hardware and use particular model from your local drive.

Args:

inference_host_address: Inference engine designator; it defines which inference engine to use.

    - For AI Server-based inference it can be either the hostname or IP address of the AI Server host,
    optionally followed by the port number in the form `:port`.

    - For DeGirum Cloud Platform-based inference it is the string `"@cloud"` or [degirum.CLOUD][] constant.

    - For local inference it is the string `"@local"` or [degirum.LOCAL][] constant.

zoo_url: Model zoo URL string which defines the model zoo to operate with.

    - For a cloud model zoo, it is specified in the following format: `<cloud server prefix>[/<zoo suffix>]`.
    The `<cloud server prefix>` part is the cloud platform root URL, typically `https://cs.degirum.com`.
    The optional `<zoo suffix>` part is the cloud zoo URL suffix in the form `<organization>/<model zoo name>`.
    You can confirm zoo URL suffix by visiting your cloud user account and opening the model zoo management page.
    If `<zoo suffix>` is not specified, then DeGirum public model zoo `degirum/public` is used.

    - For AI Server-based inferences, you may omit both `zoo_url` and `token` parameters.
    In this case locally-deployed model zoo of the AI Server will be used.

    - For local AI hardware inferences you specify `zoo_url` parameter as either a path to a local
    model zoo directory, or a path to model's .json configuration file.
    The `token` parameter is not needed in this case.

token: Cloud API access token used to access the cloud zoo.

    - To obtain this token you need to open a user account on [DeGirum cloud platform](https://cs.degirum.com).
    Please login to your account and go to the token generation page to generate an API access token.

Returns:

Type Description
ZooManager

An instance of Model Zoo manager object configured to work with AI inference host and model zoo of your choice.

Once you created Model Zoo manager object, you may use the following methods:

degirum.load_model(model_name, inference_host_address, zoo_url=None, token=None, **kwargs)

Load a model from the model zoo for the inference.

Args:

model_name: Model name to load from the model zoo.

inference_host_address: Inference engine designator; it defines which inference engine to use.

zoo_url: Model zoo URL string which defines the model zoo to operate with.

token: Cloud API access token used to access the cloud zoo.

**kwargs:
    you may pass arbitrary model properties to be assigned to the model object in a form
    of property=value

Note

For detailed description of zoo_url, inference_host_address, and token parameters refer to degirum.connect function.

Returns:

An instance of [degirum.model.Model][] model handling object to be used for AI inferences.

degirum.list_models(inference_host_address, zoo_url, token=None, **kwargs)

List models in the model zoo matching to specified filter values.

Args:

inference_host_address: Inference engine designator; it defines which inference engine to use.

zoo_url: Model zoo URL string which defines the model zoo to operate with.

token: Cloud API access token used to access the cloud zoo.

kwargs: filter parameters to narrow down the list of models.

Note

For detailed description of zoo_url, inference_host_address, and token parameters refer to degirum.connect function. For detailed description of kwargs parameters refer to degirum.ZooManager.list_models method.

Returns:

A dictionary with model names as keys and model info as values.

degirum.get_supported_devices(inference_host_address, zoo_url='')

Get runtime/device type names, which are available in the inference engine.

Args:

inference_host_address: Inference engine designator; it defines which inference engine to use.

zoo_url: Optional model zoo URL string which defines the model zoo to operate with.
    Makes sense only for cloud inference engines to specify another base URL.

Note

For detailed description of inference_host_address and token parameters refer to degirum.connect function.

Returns:

Type Description
List[str]

list of runtime/device type names; each element is a string in a format "RUNTIME/DEVICE"

degirum.enable_default_logger(level=logging.DEBUG)

Helper function for adding a StreamHandler to the package logger. Removes any existing handlers. Useful for debugging.

Args:

level: Logging level as defined in logging python package. defaults to logging.DEBUG.

Returns:

Returns an instance of added StreamHandler.