Class: Google::Apis::MlV1::GoogleCloudMlV1PredictionInput

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
generated/google/apis/ml_v1/classes.rb,
generated/google/apis/ml_v1/representations.rb,
generated/google/apis/ml_v1/representations.rb

Overview

Represents input parameters for a prediction job.

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from Core::JsonObjectSupport

#to_json

Methods included from Core::Hashable

process_value, #to_h

Constructor Details

#initialize(**args) ⇒ GoogleCloudMlV1PredictionInput

Returns a new instance of GoogleCloudMlV1PredictionInput.



1229
1230
1231
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1229

def initialize(**args)
   update!(**args)
end

Instance Attribute Details

#batch_size ⇒ Fixnum

Optional. Number of records per batch, defaults to 64. The service will buffer batch_size number of records in memory before invoking one Tensorflow prediction call internally. So take the record size and memory available into consideration when setting this parameter. Corresponds to the JSON property batchSize

Returns:

  • (Fixnum) 


1151
1152
1153
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1151

def batch_size
  @batch_size
end

#data_format ⇒ String

Required. The format of the input data files. Corresponds to the JSON property dataFormat

Returns:

  • (String) 


1156
1157
1158
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1156

def data_format
  @data_format
end

#input_paths ⇒ Array<String>

Required. The Cloud Storage location of the input data files. May contain wildcards. Corresponds to the JSON property inputPaths

Returns:

  • (Array<String>) 


1162
1163
1164
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1162

def input_paths
  @input_paths
end

#max_worker_count ⇒ Fixnum

Optional. The maximum number of workers to be used for parallel processing. Defaults to 10 if not specified. Corresponds to the JSON property maxWorkerCount

Returns:

  • (Fixnum) 


1168
1169
1170
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1168

def max_worker_count
  @max_worker_count
end

#model_name ⇒ String

Use this field if you want to use the default version for the specified model. The string must use the following format: "projects/YOUR_PROJECT/models/YOUR_MODEL" Corresponds to the JSON property modelName

Returns:

  • (String) 


1175
1176
1177
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1175

def model_name
  @model_name
end

#output_data_format ⇒ String

Optional. Format of the output data files, defaults to JSON. Corresponds to the JSON property outputDataFormat

Returns:

  • (String) 


1180
1181
1182
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1180

def output_data_format
  @output_data_format
end

#output_path ⇒ String

Required. The output Google Cloud Storage location. Corresponds to the JSON property outputPath

Returns:

  • (String) 


1185
1186
1187
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1185

def output_path
  @output_path
end

#region ⇒ String

Required. The Google Compute Engine region to run the prediction job in. See the available regions for AI Platform services. Corresponds to the JSON property region

Returns:

  • (String) 


1192
1193
1194
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1192

def region
  @region
end

#runtime_version ⇒ String

Optional. The AI Platform runtime version to use for this batch prediction. If not set, AI Platform will pick the runtime version used during the CreateVersion request for this model version, or choose the latest stable version when model version information is not available such as when the model is specified by uri. Corresponds to the JSON property runtimeVersion

Returns:

  • (String) 


1201
1202
1203
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1201

def runtime_version
  @runtime_version
end

#signature_name ⇒ String

Optional. The name of the signature defined in the SavedModel to use for this job. Please refer to SavedModel for information about how to use signatures. Defaults to DEFAULT_SERVING_SIGNATURE_DEF_KEY , which is "serving_default". Corresponds to the JSON property signatureName

Returns:

  • (String) 


1213
1214
1215
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1213

def signature_name
  @signature_name
end

#uri ⇒ String

Use this field if you want to specify a Google Cloud Storage path for the model to use. Corresponds to the JSON property uri

Returns:

  • (String) 


1219
1220
1221
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1219

def uri
  @uri
end

#version_name ⇒ String

Use this field if you want to specify a version of the model to use. The string is formatted the same way as model_version, with the addition of the version information: "projects/YOUR_PROJECT/models/YOUR_MODEL/versions/YOUR_VERSION" Corresponds to the JSON property versionName

Returns:

  • (String) 


1227
1228
1229
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1227

def version_name
  @version_name
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
 
# File 'generated/google/apis/ml_v1/classes.rb', line 1234

def update!(**args)
  @batch_size = args[:batch_size] if args.key?(:batch_size)
  @data_format = args[:data_format] if args.key?(:data_format)
  @input_paths = args[:input_paths] if args.key?(:input_paths)
  @max_worker_count = args[:max_worker_count] if args.key?(:max_worker_count)
  @model_name = args[:model_name] if args.key?(:model_name)
  @output_data_format = args[:output_data_format] if args.key?(:output_data_format)
  @output_path = args[:output_path] if args.key?(:output_path)
  @region = args[:region] if args.key?(:region)
  @runtime_version = args[:runtime_version] if args.key?(:runtime_version)
  @signature_name = args[:signature_name] if args.key?(:signature_name)
  @uri = args[:uri] if args.key?(:uri)
  @version_name = args[:version_name] if args.key?(:version_name)
end