public final class ModelExportOutputConfig extends GeneratedMessageV3 implements ModelExportOutputConfigOrBuilder
Output configuration for ModelExport Action.
Protobuf type google.cloud.automl.v1.ModelExportOutputConfig
Static Fields
GCS_DESTINATION_FIELD_NUMBER
public static final int GCS_DESTINATION_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
public static final int MODEL_FORMAT_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
PARAMS_FIELD_NUMBER
public static final int PARAMS_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
Static Methods
getDefaultInstance()
public static ModelExportOutputConfig getDefaultInstance()
getDescriptor()
public static final Descriptors.Descriptor getDescriptor()
newBuilder()
public static ModelExportOutputConfig.Builder newBuilder()
newBuilder(ModelExportOutputConfig prototype)
public static ModelExportOutputConfig.Builder newBuilder(ModelExportOutputConfig prototype)
public static ModelExportOutputConfig parseDelimitedFrom(InputStream input)
public static ModelExportOutputConfig parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
parseFrom(byte[] data)
public static ModelExportOutputConfig parseFrom(byte[] data)
| Parameter |
|---|
| Name | Description |
data | byte[]
|
parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
public static ModelExportOutputConfig parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
parseFrom(ByteString data)
public static ModelExportOutputConfig parseFrom(ByteString data)
parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
public static ModelExportOutputConfig parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
public static ModelExportOutputConfig parseFrom(CodedInputStream input)
public static ModelExportOutputConfig parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
public static ModelExportOutputConfig parseFrom(InputStream input)
public static ModelExportOutputConfig parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
parseFrom(ByteBuffer data)
public static ModelExportOutputConfig parseFrom(ByteBuffer data)
parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
public static ModelExportOutputConfig parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
parser()
public static Parser<ModelExportOutputConfig> parser()
Methods
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 |
|---|
| Name | Description |
key | String
|
equals(Object obj)
public boolean equals(Object obj)
| Parameter |
|---|
| Name | Description |
obj | Object
|
Overrides
getDefaultInstanceForType()
public ModelExportOutputConfig getDefaultInstanceForType()
getDestinationCase()
public ModelExportOutputConfig.DestinationCase getDestinationCase()
getGcsDestination()
public GcsDestination getGcsDestination()
Required. 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.v1.GcsDestination gcs_destination = 1 [(.google.api.field_behavior) = REQUIRED];
getGcsDestinationOrBuilder()
public GcsDestinationOrBuilder getGcsDestinationOrBuilder()
Required. 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.v1.GcsDestination gcs_destination = 1 [(.google.api.field_behavior) = REQUIRED];
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".
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 |
|---|
| Type | Description |
String | The modelFormat.
|
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".
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 |
|---|
| Type | Description |
ByteString | The bytes for modelFormat.
|
getParams()
public Map<String,String> getParams()
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 |
|---|
| Type | Description |
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;
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;
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 |
|---|
| Name | Description |
key | String
|
getParserForType()
public Parser<ModelExportOutputConfig> getParserForType()
Overrides
getSerializedSize()
public int getSerializedSize()
| Returns |
|---|
| Type | Description |
int | |
Overrides
getUnknownFields()
public final UnknownFieldSet getUnknownFields()
Overrides
hasGcsDestination()
public boolean hasGcsDestination()
Required. 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.v1.GcsDestination gcs_destination = 1 [(.google.api.field_behavior) = REQUIRED];
| Returns |
|---|
| Type | Description |
boolean | Whether the gcsDestination field is set.
|
hashCode()
| Returns |
|---|
| Type | Description |
int | |
Overrides
internalGetFieldAccessorTable()
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Overrides
internalGetMapField(int number)
protected MapField internalGetMapField(int number)
| Parameter |
|---|
| Name | Description |
number | int
|
Overrides
isInitialized()
public final boolean isInitialized()
Overrides
newBuilderForType()
public ModelExportOutputConfig.Builder newBuilderForType()
newBuilderForType(GeneratedMessageV3.BuilderParent parent)
protected ModelExportOutputConfig.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Overrides
newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Overrides
toBuilder()
public ModelExportOutputConfig.Builder toBuilder()
writeTo(CodedOutputStream output)
public void writeTo(CodedOutputStream output)
Overrides
