Class ModelExportOutputConfig.Builder (2.6.0)

public static final class ModelExportOutputConfig.Builder extends GeneratedMessageV3.Builder<ModelExportOutputConfig.Builder> implements ModelExportOutputConfigOrBuilder

Output configuration for ModelExport Action.

Protobuf type google.cloud.automl.v1beta1.ModelExportOutputConfig

Static Methods

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
TypeDescription
Descriptor

Methods

addRepeatedField(Descriptors.FieldDescriptor field, Object value)

public ModelExportOutputConfig.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
ModelExportOutputConfig.Builder
Overrides

build()

public ModelExportOutputConfig build()
Returns
TypeDescription
ModelExportOutputConfig

buildPartial()

public ModelExportOutputConfig buildPartial()
Returns
TypeDescription
ModelExportOutputConfig

clear()

public ModelExportOutputConfig.Builder clear()
Returns
TypeDescription
ModelExportOutputConfig.Builder
Overrides

clearDestination()

public ModelExportOutputConfig.Builder clearDestination()
Returns
TypeDescription
ModelExportOutputConfig.Builder

clearField(Descriptors.FieldDescriptor field)

public ModelExportOutputConfig.Builder clearField(Descriptors.FieldDescriptor field)
Parameter
NameDescription
fieldFieldDescriptor
Returns
TypeDescription
ModelExportOutputConfig.Builder
Overrides

clearGcrDestination()

public ModelExportOutputConfig.Builder clearGcrDestination()

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.

.google.cloud.automl.v1beta1.GcrDestination gcr_destination = 3;

Returns
TypeDescription
ModelExportOutputConfig.Builder

clearGcsDestination()

public ModelExportOutputConfig.Builder clearGcsDestination()

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-<model-display-name>-<timestamp-of-export-call>", where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format, will be created. Inside the model and any of its supporting files will be written.

.google.cloud.automl.v1beta1.GcsDestination gcs_destination = 1;

Returns
TypeDescription
ModelExportOutputConfig.Builder

clearModelFormat()

public ModelExportOutputConfig.Builder clearModelFormat()

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
  • core_ml - Used for iOS mobile devices.

string model_format = 4;

Returns
TypeDescription
ModelExportOutputConfig.Builder

This builder for chaining.

clearOneof(Descriptors.OneofDescriptor oneof)

public ModelExportOutputConfig.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter
NameDescription
oneofOneofDescriptor
Returns
TypeDescription
ModelExportOutputConfig.Builder
Overrides

clearParams()

public ModelExportOutputConfig.Builder clearParams()
Returns
TypeDescription
ModelExportOutputConfig.Builder

clone()

public ModelExportOutputConfig.Builder clone()
Returns
TypeDescription
ModelExportOutputConfig.Builder
Overrides

containsParams(String key)

public boolean containsParams(String key)

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".

map<string, string> params = 2;

Parameter
NameDescription
keyString
Returns
TypeDescription
boolean

getDefaultInstanceForType()

public ModelExportOutputConfig getDefaultInstanceForType()
Returns
TypeDescription
ModelExportOutputConfig

getDescriptorForType()

public Descriptors.Descriptor getDescriptorForType()
Returns
TypeDescription
Descriptor
Overrides

getDestinationCase()

public ModelExportOutputConfig.DestinationCase getDestinationCase()
Returns
TypeDescription
ModelExportOutputConfig.DestinationCase

getGcrDestination()

public GcrDestination 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.

.google.cloud.automl.v1beta1.GcrDestination gcr_destination = 3;

Returns
TypeDescription
GcrDestination

The gcrDestination.

getGcrDestinationBuilder()

public GcrDestination.Builder getGcrDestinationBuilder()

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.

.google.cloud.automl.v1beta1.GcrDestination gcr_destination = 3;

Returns
TypeDescription
GcrDestination.Builder

getGcrDestinationOrBuilder()

public GcrDestinationOrBuilder getGcrDestinationOrBuilder()

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.

.google.cloud.automl.v1beta1.GcrDestination gcr_destination = 3;

Returns
TypeDescription
GcrDestinationOrBuilder

getGcsDestination()

public GcsDestination 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-<model-display-name>-<timestamp-of-export-call>", where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format, will be created. Inside the model and any of its supporting files will be written.

.google.cloud.automl.v1beta1.GcsDestination gcs_destination = 1;

Returns
TypeDescription
GcsDestination

The gcsDestination.

getGcsDestinationBuilder()

public GcsDestination.Builder getGcsDestinationBuilder()

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-<model-display-name>-<timestamp-of-export-call>", where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format, will be created. Inside the model and any of its supporting files will be written.

.google.cloud.automl.v1beta1.GcsDestination gcs_destination = 1;

Returns
TypeDescription
GcsDestination.Builder

getGcsDestinationOrBuilder()

public GcsDestinationOrBuilder getGcsDestinationOrBuilder()

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-<model-display-name>-<timestamp-of-export-call>", where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format, will be created. Inside the model and any of its supporting files will be written.

.google.cloud.automl.v1beta1.GcsDestination gcs_destination = 1;

Returns
TypeDescription
GcsDestinationOrBuilder

getModelFormat()

public String 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
  • core_ml - Used for iOS mobile devices.

string model_format = 4;

Returns
TypeDescription
String

The modelFormat.

getModelFormatBytes()

public ByteString getModelFormatBytes()

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
  • core_ml - Used for iOS mobile devices.

string model_format = 4;

Returns
TypeDescription
ByteString

The bytes for modelFormat.

getMutableParams()

public Map<String,String> getMutableParams()

Use alternate mutation accessors instead.

Returns
TypeDescription
Map<String,String>

getParams()

public Map<String,String> getParams()

Use #getParamsMap() instead.

Returns
TypeDescription
Map<String,String>

getParamsCount()

public int getParamsCount()

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".

map<string, string> params = 2;

Returns
TypeDescription
int

getParamsMap()

public Map<String,String> getParamsMap()

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".

map<string, string> params = 2;

Returns
TypeDescription
Map<String,String>

getParamsOrDefault(String key, String defaultValue)

public String getParamsOrDefault(String key, String defaultValue)

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".

map<string, string> params = 2;

Parameters
NameDescription
keyString
defaultValueString
Returns
TypeDescription
String

getParamsOrThrow(String key)

public String getParamsOrThrow(String key)

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".

map<string, string> params = 2;

Parameter
NameDescription
keyString
Returns
TypeDescription
String

hasGcrDestination()

public boolean hasGcrDestination()

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.

.google.cloud.automl.v1beta1.GcrDestination gcr_destination = 3;

Returns
TypeDescription
boolean

Whether the gcrDestination field is set.

hasGcsDestination()

public boolean hasGcsDestination()

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-<model-display-name>-<timestamp-of-export-call>", where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format, will be created. Inside the model and any of its supporting files will be written.

.google.cloud.automl.v1beta1.GcsDestination gcs_destination = 1;

Returns
TypeDescription
boolean

Whether the gcsDestination field is set.

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
TypeDescription
FieldAccessorTable
Overrides

internalGetMapField(int number)

protected MapField internalGetMapField(int number)
Parameter
NameDescription
numberint
Returns
TypeDescription
MapField
Overrides

internalGetMutableMapField(int number)

protected MapField internalGetMutableMapField(int number)
Parameter
NameDescription
numberint
Returns
TypeDescription
MapField
Overrides

isInitialized()

public final boolean isInitialized()
Returns
TypeDescription
boolean
Overrides

mergeFrom(ModelExportOutputConfig other)

public ModelExportOutputConfig.Builder mergeFrom(ModelExportOutputConfig other)
Parameter
NameDescription
otherModelExportOutputConfig
Returns
TypeDescription
ModelExportOutputConfig.Builder

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public ModelExportOutputConfig.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputCodedInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
ModelExportOutputConfig.Builder
Overrides Exceptions
TypeDescription
IOException

mergeFrom(Message other)

public ModelExportOutputConfig.Builder mergeFrom(Message other)
Parameter
NameDescription
otherMessage
Returns
TypeDescription
ModelExportOutputConfig.Builder
Overrides

mergeGcrDestination(GcrDestination value)

public ModelExportOutputConfig.Builder mergeGcrDestination(GcrDestination value)

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.

.google.cloud.automl.v1beta1.GcrDestination gcr_destination = 3;

Parameter
NameDescription
valueGcrDestination
Returns
TypeDescription
ModelExportOutputConfig.Builder

mergeGcsDestination(GcsDestination value)

public ModelExportOutputConfig.Builder mergeGcsDestination(GcsDestination value)

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-<model-display-name>-<timestamp-of-export-call>", where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format, will be created. Inside the model and any of its supporting files will be written.

.google.cloud.automl.v1beta1.GcsDestination gcs_destination = 1;

Parameter
NameDescription
valueGcsDestination
Returns
TypeDescription
ModelExportOutputConfig.Builder

mergeUnknownFields(UnknownFieldSet unknownFields)

public final ModelExportOutputConfig.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
ModelExportOutputConfig.Builder
Overrides

putAllParams(Map<String,String> values)

public ModelExportOutputConfig.Builder putAllParams(Map<String,String> values)

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".

map<string, string> params = 2;

Parameter
NameDescription
valuesMap<String,String>
Returns
TypeDescription
ModelExportOutputConfig.Builder

putParams(String key, String value)

public ModelExportOutputConfig.Builder putParams(String key, String value)

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".

map<string, string> params = 2;

Parameters
NameDescription
keyString
valueString
Returns
TypeDescription
ModelExportOutputConfig.Builder

removeParams(String key)

public ModelExportOutputConfig.Builder removeParams(String key)

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".

map<string, string> params = 2;

Parameter
NameDescription
keyString
Returns
TypeDescription
ModelExportOutputConfig.Builder

setField(Descriptors.FieldDescriptor field, Object value)

public ModelExportOutputConfig.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
ModelExportOutputConfig.Builder
Overrides

setGcrDestination(GcrDestination value)

public ModelExportOutputConfig.Builder setGcrDestination(GcrDestination value)

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.

.google.cloud.automl.v1beta1.GcrDestination gcr_destination = 3;

Parameter
NameDescription
valueGcrDestination
Returns
TypeDescription
ModelExportOutputConfig.Builder

setGcrDestination(GcrDestination.Builder builderForValue)

public ModelExportOutputConfig.Builder setGcrDestination(GcrDestination.Builder builderForValue)

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.

.google.cloud.automl.v1beta1.GcrDestination gcr_destination = 3;

Parameter
NameDescription
builderForValueGcrDestination.Builder
Returns
TypeDescription
ModelExportOutputConfig.Builder

setGcsDestination(GcsDestination value)

public ModelExportOutputConfig.Builder setGcsDestination(GcsDestination value)

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-<model-display-name>-<timestamp-of-export-call>", where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format, will be created. Inside the model and any of its supporting files will be written.

.google.cloud.automl.v1beta1.GcsDestination gcs_destination = 1;

Parameter
NameDescription
valueGcsDestination
Returns
TypeDescription
ModelExportOutputConfig.Builder

setGcsDestination(GcsDestination.Builder builderForValue)

public ModelExportOutputConfig.Builder setGcsDestination(GcsDestination.Builder builderForValue)

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-<model-display-name>-<timestamp-of-export-call>", where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format, will be created. Inside the model and any of its supporting files will be written.

.google.cloud.automl.v1beta1.GcsDestination gcs_destination = 1;

Parameter
NameDescription
builderForValueGcsDestination.Builder
Returns
TypeDescription
ModelExportOutputConfig.Builder

setModelFormat(String value)

public ModelExportOutputConfig.Builder setModelFormat(String value)

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
  • core_ml - Used for iOS mobile devices.

string model_format = 4;

Parameter
NameDescription
valueString

The modelFormat to set.

Returns
TypeDescription
ModelExportOutputConfig.Builder

This builder for chaining.

setModelFormatBytes(ByteString value)

public ModelExportOutputConfig.Builder setModelFormatBytes(ByteString value)

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
  • core_ml - Used for iOS mobile devices.

string model_format = 4;

Parameter
NameDescription
valueByteString

The bytes for modelFormat to set.

Returns
TypeDescription
ModelExportOutputConfig.Builder

This builder for chaining.

setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)

public ModelExportOutputConfig.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters
NameDescription
fieldFieldDescriptor
indexint
valueObject
Returns
TypeDescription
ModelExportOutputConfig.Builder
Overrides

setUnknownFields(UnknownFieldSet unknownFields)

public final ModelExportOutputConfig.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
ModelExportOutputConfig.Builder
Overrides