Cloud AutoML V1beta1 Client - Class ModelExportOutputConfig (1.6.5)

Reference documentation and code samples for the Cloud AutoML V1beta1 Client class ModelExportOutputConfig.

Output configuration for ModelExport Action.

Generated from protobuf message google.cloud.automl.v1beta1.ModelExportOutputConfig

Namespace

Google \ Cloud \ AutoMl \ V1beta1

Methods

__construct

Constructor.

Parameters
Name Description
data array

Optional. Data for populating the Message object.

↳ gcs_destination Google\Cloud\AutoMl\V1beta1\GcsDestination

The Google Cloud Storage location where the model is to be written to. This location may only be set for the following model formats: "tflite", "edgetpu_tflite", "tf_saved_model", "tf_js", "core_ml". Under the directory given as the destination a new one with name "model-export-

↳ gcr_destination Google\Cloud\AutoMl\V1beta1\GcrDestination

The GCR location where model image is to be pushed to. This location may only be set for the following model formats: "docker". The model image will be created under the given URI.

↳ model_format string

The format in which the model must be exported. The available, and default, formats depend on the problem and model type (if given problem and type combination doesn't have a format listed, it means its models are not exportable): * For Image Classification mobile-low-latency-1, mobile-versatile-1, mobile-high-accuracy-1: "tflite" (default), "edgetpu_tflite", "tf_saved_model", "tf_js", "docker". * For Image Classification mobile-core-ml-low-latency-1, mobile-core-ml-versatile-1, mobile-core-ml-high-accuracy-1: "core_ml" (default). * For Image Object Detection mobile-low-latency-1, mobile-versatile-1, mobile-high-accuracy-1: "tflite", "tf_saved_model", "tf_js". * For Video Classification cloud, "tf_saved_model". * For Video Object Tracking cloud, "tf_saved_model". * For Video Object Tracking mobile-versatile-1: "tflite", "edgetpu_tflite", "tf_saved_model", "docker". * For Video Object Tracking mobile-coral-versatile-1: "tflite", "edgetpu_tflite", "docker". * For Video Object Tracking mobile-coral-low-latency-1: "tflite", "edgetpu_tflite", "docker". * For Video Object Tracking mobile-jetson-versatile-1: "tf_saved_model", "docker". * For Tables: "docker". Formats description: * tflite - Used for Android mobile devices. * edgetpu_tflite - Used for Edge TPU devices. * tf_saved_model - A tensorflow model in SavedModel format. * tf_js - A TensorFlow.js model that can be used in the browser and in Node.js using JavaScript. * docker - Used for Docker containers. Use the params field to customize the container. The container is verified to work correctly on ubuntu 16.04 operating system. See more at [containers quickstart](https: //cloud.google.com/vision/automl/docs/containers-gcs-quickstart) * core_ml - Used for iOS mobile devices.

↳ params array|Google\Protobuf\Internal\MapField

Additional model-type and format specific parameters describing the requirements for the to be exported model files, any string must be up to 25000 characters long. * For docker format: cpu_architecture - (string) "x86_64" (default). gpu_architecture - (string) "none" (default), "nvidia".

getGcsDestination

The Google Cloud Storage location where the model is to be written to.

This location may only be set for the following model formats: "tflite", "edgetpu_tflite", "tf_saved_model", "tf_js", "core_ml". Under the directory given as the destination a new one with name "model-export-

Returns
Type Description
Google\Cloud\AutoMl\V1beta1\GcsDestination|null

hasGcsDestination

setGcsDestination

The Google Cloud Storage location where the model is to be written to.

This location may only be set for the following model formats: "tflite", "edgetpu_tflite", "tf_saved_model", "tf_js", "core_ml". Under the directory given as the destination a new one with name "model-export-

Parameter
Name Description
var Google\Cloud\AutoMl\V1beta1\GcsDestination
Returns
Type Description
$this

getGcrDestination

The GCR location where model image is to be pushed to. This location may only be set for the following model formats: "docker".

The model image will be created under the given URI.

Returns
Type Description
Google\Cloud\AutoMl\V1beta1\GcrDestination|null

hasGcrDestination

setGcrDestination

The GCR location where model image is to be pushed to. This location may only be set for the following model formats: "docker".

The model image will be created under the given URI.

Parameter
Name Description
var Google\Cloud\AutoMl\V1beta1\GcrDestination
Returns
Type Description
$this

getModelFormat

The format in which the model must be exported. The available, and default, formats depend on the problem and model type (if given problem and type combination doesn't have a format listed, it means its models are not exportable):

  • For Image Classification mobile-low-latency-1, mobile-versatile-1, mobile-high-accuracy-1: "tflite" (default), "edgetpu_tflite", "tf_saved_model", "tf_js", "docker".

  • For Image Classification mobile-core-ml-low-latency-1, mobile-core-ml-versatile-1, mobile-core-ml-high-accuracy-1: "core_ml" (default).

  • For Image Object Detection mobile-low-latency-1, mobile-versatile-1, mobile-high-accuracy-1: "tflite", "tf_saved_model", "tf_js".
  • For Video Classification cloud, "tf_saved_model".
  • For Video Object Tracking cloud, "tf_saved_model".
  • For Video Object Tracking mobile-versatile-1: "tflite", "edgetpu_tflite", "tf_saved_model", "docker".
  • For Video Object Tracking mobile-coral-versatile-1: "tflite", "edgetpu_tflite", "docker".
  • For Video Object Tracking mobile-coral-low-latency-1: "tflite", "edgetpu_tflite", "docker".
  • For Video Object Tracking mobile-jetson-versatile-1: "tf_saved_model", "docker".
  • For Tables: "docker". Formats description:
  • tflite - Used for Android mobile devices.
  • edgetpu_tflite - Used for Edge TPU devices.
  • tf_saved_model - A tensorflow model in SavedModel format.
  • tf_js - A TensorFlow.js model that can be used in the browser and in Node.js using JavaScript.
  • docker - Used for Docker containers. Use the params field to customize the container. The container is verified to work correctly on ubuntu 16.04 operating system. See more at [containers quickstart](https: //cloud.google.com/vision/automl/docs/containers-gcs-quickstart)
  • core_ml - Used for iOS mobile devices.
Returns
Type Description
string

setModelFormat

The format in which the model must be exported. The available, and default, formats depend on the problem and model type (if given problem and type combination doesn't have a format listed, it means its models are not exportable):

  • For Image Classification mobile-low-latency-1, mobile-versatile-1, mobile-high-accuracy-1: "tflite" (default), "edgetpu_tflite", "tf_saved_model", "tf_js", "docker".

  • For Image Classification mobile-core-ml-low-latency-1, mobile-core-ml-versatile-1, mobile-core-ml-high-accuracy-1: "core_ml" (default).

  • For Image Object Detection mobile-low-latency-1, mobile-versatile-1, mobile-high-accuracy-1: "tflite", "tf_saved_model", "tf_js".
  • For Video Classification cloud, "tf_saved_model".
  • For Video Object Tracking cloud, "tf_saved_model".
  • For Video Object Tracking mobile-versatile-1: "tflite", "edgetpu_tflite", "tf_saved_model", "docker".
  • For Video Object Tracking mobile-coral-versatile-1: "tflite", "edgetpu_tflite", "docker".
  • For Video Object Tracking mobile-coral-low-latency-1: "tflite", "edgetpu_tflite", "docker".
  • For Video Object Tracking mobile-jetson-versatile-1: "tf_saved_model", "docker".
  • For Tables: "docker". Formats description:
  • tflite - Used for Android mobile devices.
  • edgetpu_tflite - Used for Edge TPU devices.
  • tf_saved_model - A tensorflow model in SavedModel format.
  • tf_js - A TensorFlow.js model that can be used in the browser and in Node.js using JavaScript.
  • docker - Used for Docker containers. Use the params field to customize the container. The container is verified to work correctly on ubuntu 16.04 operating system. See more at [containers quickstart](https: //cloud.google.com/vision/automl/docs/containers-gcs-quickstart)
  • core_ml - Used for iOS mobile devices.
Parameter
Name Description
var string
Returns
Type Description
$this

getParams

Additional model-type and format specific parameters describing the requirements for the to be exported model files, any string must be up to 25000 characters long.

  • For docker format: cpu_architecture - (string) "x86_64" (default). gpu_architecture - (string) "none" (default), "nvidia".
Returns
Type Description
Google\Protobuf\Internal\MapField

setParams

Additional model-type and format specific parameters describing the requirements for the to be exported model files, any string must be up to 25000 characters long.

  • For docker format: cpu_architecture - (string) "x86_64" (default). gpu_architecture - (string) "none" (default), "nvidia".
Parameter
Name Description
var array|Google\Protobuf\Internal\MapField
Returns
Type Description
$this

getDestination

Returns
Type Description
string