View Source API Reference google_api_language v0.16.0
Modules
API client metadata for GoogleApi.Language.V1.
API calls for all endpoints tagged Documents
.
Handle Tesla connections for GoogleApi.Language.V1.
The entity analysis request message.
The entity analysis response message.
The entity-level sentiment analysis request message.
The entity-level sentiment analysis response message.
The sentiment analysis request message.
The sentiment analysis response message.
The syntax analysis request message.
The syntax analysis response message.
The request message for the text annotation API, which can perform multiple analysis types (sentiment, entities, and syntax) in one call.
All available features for sentiment, syntax, and semantic analysis. Setting each one to true will enable that specific analysis for the input.
The text annotations response message.
Represents a category returned from the text classifier.
Model options available for classification requests.
Options for the V1 model.
Options for the V2 model.
The document classification request message.
The document classification response message.
Represents a color in the RGBA color space. This representation is designed for simplicity of conversion to and from color representations in various languages over compactness. For example, the fields of this representation can be trivially provided to the constructor of java.awt.Color
in Java; it can also be trivially provided to UIColor's +colorWithRed:green:blue:alpha
method in iOS; and, with just a little work, it can be easily formatted into a CSS rgba()
string in JavaScript. This reference page doesn't have information about the absolute color space that should be used to interpret the RGB value—for example, sRGB, Adobe RGB, DCI-P3, and BT.2020. By default, applications should assume the sRGB color space. When color equality needs to be decided, implementations, unless documented otherwise, treat two colors as equal if all their red, green, blue, and alpha values each differ by at most 1e-5
. Example (Java): import com.google.type.Color; // ... public static java.awt.Color fromProto(Color protocolor) { float alpha = protocolor.hasAlpha() ? protocolor.getAlpha().getValue() : 1.0; return new java.awt.Color( protocolor.getRed(), protocolor.getGreen(), protocolor.getBlue(), alpha); } public static Color toProto(java.awt.Color color) { float red = (float) color.getRed(); float green = (float) color.getGreen(); float blue = (float) color.getBlue(); float denominator = 255.0; Color.Builder resultBuilder = Color .newBuilder() .setRed(red / denominator) .setGreen(green / denominator) .setBlue(blue / denominator); int alpha = color.getAlpha(); if (alpha != 255) { result.setAlpha( FloatValue .newBuilder() .setValue(((float) alpha) / denominator) .build()); } return resultBuilder.build(); } // ... Example (iOS / Obj-C): // ... static UIColor fromProto(Color protocolor) { float red = [protocolor red]; float green = [protocolor green]; float blue = [protocolor blue]; FloatValue alpha_wrapper = [protocolor alpha]; float alpha = 1.0; if (alpha_wrapper != nil) { alpha = [alpha_wrapper value]; } return [UIColor colorWithRed:red green:green blue:blue alpha:alpha]; } static Color toProto(UIColor color) { CGFloat red, green, blue, alpha; if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) { return nil; } Color result = [[Color alloc] init]; [result setRed:red]; [result setGreen:green]; [result setBlue:blue]; if (alpha <= 0.9999) { [result setAlpha:floatWrapperWithValue(alpha)]; } [result autorelease]; return result; } // ... Example (JavaScript): // ... var protoToCssColor = function(rgb_color) { var redFrac = rgb_color.red || 0.0; var greenFrac = rgb_color.green || 0.0; var blueFrac = rgb_color.blue || 0.0; var red = Math.floor(redFrac 255); var green = Math.floor(greenFrac 255); var blue = Math.floor(blueFrac * 255); if (!('alpha' in rgb_color)) { return rgbToCssColor(red, green, blue); } var alphaFrac = rgb_color.alpha.value || 0.0; var rgbParams = [red, green, blue].join(','); return ['rgba(', rgbParams, ',', alphaFrac, ')'].join(''); }; var rgbToCssColor = function(red, green, blue) { var rgbNumber = new Number((red << 16) | (green << 8) | blue); var hexString = rgbNumber.toString(16); var missingZeros = 6 - hexString.length; var resultBuilder = ['#']; for (var i = 0; i < missingZeros; i++) { resultBuilder.push('0'); } resultBuilder.push(hexString); return resultBuilder.join(''); }; // ...
Metric for billing reports.
Represents dependency parse tree information for a token. (For more information on dependency labels, see http://www.aclweb.org/anthology/P13-2017
Represents the input to API methods.
Represents a phrase in the text that is a known entity, such as a person, an organization, or location. The API associates information, such as salience and mentions, with entities.
Represents a mention for an entity in the text. Currently, proper noun mentions are supported.
Attributes
-
gpuSec
(type:String.t
, default:nil
) - Required. Seconds of GPU usage, e.g. 3600. -
gpuType
(type:String.t
, default:nil
) - Required. Type of GPU, e.g. NVIDIA_TESLA_V100. -
machineSpec
(type:String.t
, default:nil
) - Required. Machine spec, e.g. N1_STANDARD_4. -
trackingLabels
(type:map()
, default:nil
) - Billing tracking labels. They do not contain any user data but only the labels set by Vertex Core Infra itself. Tracking labels' keys are defined with special format: goog-[\p{Ll}\p{N}]+ E.g. "key": "goog-k8s-cluster-name","value": "us-east1-b4rk"
Infra Usage of billing metrics. Next ID: 6
The document moderation request message.
The document moderation response message.
Represents part of speech information for a token. Parts of speech are as defined in http://www.lrec-conf.org/proceedings/lrec2012/pdf/274_Paper.pdf
Attributes
-
gibSec
(type:String.t
, default:nil
) - Required. VM memory in Gigabyte second, e.g. 3600. Using int64 type to match billing metrics definition. -
machineSpec
(type:String.t
, default:nil
) - Required. Machine spec, e.g. N1_STANDARD_4. -
memories
(type:float()
, default:nil
) - Required. VM memory in gb. -
ramType
(type:String.t
, default:nil
) - Required. Type of ram. -
trackingLabels
(type:map()
, default:nil
) - Billing tracking labels. They do not contain any user data but only the labels set by Vertex Core Infra itself. Tracking labels' keys are defined with special format: goog-[\p{Ll}\p{N}]+ E.g. "key": "goog-k8s-cluster-name","value": "us-east1-b4rk"
Represents a sentence in the input document.
Represents the feeling associated with the entire text or entities in the text.
The Status
type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC. Each Status
message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the API Design Guide.
Represents a text span in the input document.
Represents the smallest syntactic building block of the text.
The data statistics of a series of ARRAY values.
Bounding box matching model metrics for a single intersection-over-union threshold and multiple label match confidence thresholds.
Metrics for a single confidence threshold.
The data statistics of a series of CATEGORY values.
The statistics of a single CATEGORY value.
Model evaluation metrics for classification problems. It can be used for image and video classification. Next tag: 9.
Map from color to display name. Will only be used by Image Segmentation for uCAIP.
RGB color and each channel is represented by an integer.
Attributes
-
columnId
(type:integer()
, default:nil
) - The unique id of the column. When Preprocess, the Tables BE will popuate the order id of the column, which reflects the order of the column inside the table, i.e. 0 means the first column in the table, N-1 means the last column. AutoML BE will persist this order id in Spanner and set the order id here when calling RefreshTablesStats and Train. Note: it's different than the column_spec_id that is generated in AutoML BE. -
dataStats
(type:GoogleApi.Language.V1.Model.XPSDataStats.t
, default:nil
) - The data stats of the column. It's outputed in RefreshTablesStats and a required input for Train. -
dataType
(type:GoogleApi.Language.V1.Model.XPSDataType.t
, default:nil
) - The data type of the column. It's outputed in Preprocess rpc and a required input for RefreshTablesStats and Train. -
displayName
(type:String.t
, default:nil
) - The display name of the column. It's outputed in Preprocess and a required input for RefreshTablesStats and Train. -
forecastingMetadata
(type:GoogleApi.Language.V1.Model.XPSColumnSpecForecastingMetadata.t
, default:nil
) - -
topCorrelatedColumns
(type:list(GoogleApi.Language.V1.Model.XPSColumnSpecCorrelatedColumn.t)
, default:nil
) - It's outputed in RefreshTablesStats, and a required input in Train.
Identifies a table's column, and its correlation with the column this ColumnSpec describes.
=========================================================================== # The fields below are used exclusively for Forecasting.
Common statistics for a column with a specified data type.
ConfidenceMetricsEntry includes generic precision, recall, f1 score etc. Next tag: 16.
Confusion matrix of the model running the classification.
A row in the confusion matrix.
A model format used for iOS mobile devices.
A correlation statistics between two series of DataType values. The series may have differing DataType-s, but within a single series the DataType must be the same.
Different types of errors and the stats associatesd with each error.
The data statistics of a series of values that share the same DataType.
Indicated the type of data that can be stored in a structured data entity (e.g. a table).
A model format 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.
A model format used for Edge TPU devices.
Contains xPS-specific model evaluation metrics either for a single annotation spec (label), or for the model overall. Next tag: 18.
Specifies location of model evaluation metrics.
Set of examples or input sources.
Attributes
-
coreMlFormat
(type:GoogleApi.Language.V1.Model.XPSCoreMlFormat.t
, default:nil
) - -
dockerFormat
(type:GoogleApi.Language.V1.Model.XPSDockerFormat.t
, default:nil
) - -
edgeTpuTfLiteFormat
(type:GoogleApi.Language.V1.Model.XPSEdgeTpuTfLiteFormat.t
, default:nil
) - -
exportFirebaseAuxiliaryInfo
(type:boolean()
, default:nil
) - For any model and format: If true, will additionally export FirebaseExportedModelInfo in a firebase.txt file. -
outputGcrUri
(type:String.t
, default:nil
) - The Google Contained Registry (GCR) path the exported files to be pushed to. This location is set if the exported format is DOCKDER. -
outputGcsUri
(type:String.t
, default:nil
) - The Google Cloud Storage (GCS) directory where XPS will output the exported models and related files. Format: gs://bucket/directory -
tfJsFormat
(type:GoogleApi.Language.V1.Model.XPSTfJsFormat.t
, default:nil
) - -
tfLiteFormat
(type:GoogleApi.Language.V1.Model.XPSTfLiteFormat.t
, default:nil
) - -
tfSavedModelFormat
(type:GoogleApi.Language.V1.Model.XPSTfSavedModelFormat.t
, default:nil
) -
Spec of input and output files, on external file systems (CNS, GCS, etc).
The data statistics of a series of FLOAT64 values.
A bucket of a histogram.
Attributes
-
classCount
(type:String.t
, default:nil
) - Total number of classes. -
exportModelSpec
(type:GoogleApi.Language.V1.Model.XPSImageExportModelSpec.t
, default:nil
) - Information of downloadable models that are pre-generated as part of training flow and will be persisted in AutoMl backend. Populated for AutoMl requests. -
modelArtifactSpec
(type:GoogleApi.Language.V1.Model.XPSImageModelArtifactSpec.t
, default:nil
) - ## The fields below are only populated under uCAIP request scope. -
modelServingSpec
(type:GoogleApi.Language.V1.Model.XPSImageModelServingSpec.t
, default:nil
) - -
stopReason
(type:String.t
, default:nil
) - Stop reason for training job, e.g. 'TRAIN_BUDGET_REACHED', 'MODEL_CONVERGED', 'MODEL_EARLY_STOPPED'. -
trainCostInNodeTime
(type:String.t
, default:nil
) - The actual cost to create this model. - For edge type model, the cost is expressed in node hour. - For cloud type model,the cost is expressed in compute hour. - Populated for models created before GA. To be deprecated after GA. -
trainCostNodeSeconds
(type:String.t
, default:nil
) - The actual training cost, expressed in node seconds. Populated for models trained in node time.
Information of downloadable models that are pre-generated as part of training flow and will be persisted in AutoMl backend. Upon receiving ExportModel request from user, AutoMl backend can serve the pre-generated models to user if exists (by copying the files from internal path to user provided location), otherwise, AutoMl backend will call xPS ExportModel API to generate the model on the fly with the requesting format.
Stores the locations and related metadata of the model artifacts. Populated for uCAIP requests only.
Serving specification for image models.
Model evaluation metrics for image object detection problems. Evaluates prediction quality of labeled bounding boxes.
Attributes
-
classCount
(type:String.t
, default:nil
) - Total number of classes. -
exportModelSpec
(type:GoogleApi.Language.V1.Model.XPSImageExportModelSpec.t
, default:nil
) - -
maxBoundingBoxCount
(type:String.t
, default:nil
) - Max number of bounding box. -
modelArtifactSpec
(type:GoogleApi.Language.V1.Model.XPSImageModelArtifactSpec.t
, default:nil
) - ## The fields below are only populated under uCAIP request scope. -
modelServingSpec
(type:GoogleApi.Language.V1.Model.XPSImageModelServingSpec.t
, default:nil
) - -
stopReason
(type:String.t
, default:nil
) - Stop reason for training job, e.g. 'TRAIN_BUDGET_REACHED', 'MODEL_CONVERGED'. -
trainCostNodeSeconds
(type:String.t
, default:nil
) - The actual train cost of creating this model, expressed in node seconds, i.e. 3,600 value in this field means 1 node hour.
Model evaluation metrics for image segmentation problems. Next tag: 4.
Metrics for a single confidence threshold.
Attributes
-
colorMaps
(type:list(GoogleApi.Language.V1.Model.XPSColorMap.t)
, default:nil
) - Color map of the model. -
exportModelSpec
(type:GoogleApi.Language.V1.Model.XPSImageExportModelSpec.t
, default:nil
) - NOTE: These fields are not used/needed in EAP but will be set later. -
modelArtifactSpec
(type:GoogleApi.Language.V1.Model.XPSImageModelArtifactSpec.t
, default:nil
) - ## The fields below are only populated under uCAIP request scope. Model artifact spec stores and model gcs pathes and related metadata -
modelServingSpec
(type:GoogleApi.Language.V1.Model.XPSImageModelServingSpec.t
, default:nil
) - -
stopReason
(type:String.t
, default:nil
) - Stop reason for training job, e.g. 'TRAIN_BUDGET_REACHED', 'MODEL_CONVERGED'. -
trainCostNodeSeconds
(type:String.t
, default:nil
) - The actual train cost of creating this model, expressed in node seconds, i.e. 3,600 value in this field means 1 node hour.
An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
Attributes
-
argentumMetricId
(type:String.t
, default:nil
) - For billing metrics that are using legacy sku's, set the legacy billing metric id here. This will be sent to Chemist as the "cloudbilling.googleapis.com/argentum_metric_id" label. Otherwise leave empty. -
doubleValue
(type:float()
, default:nil
) - A double value. -
int64Value
(type:String.t
, default:nil
) - A signed 64-bit integer value. -
metricName
(type:String.t
, default:nil
) - The metric name defined in the service configuration. -
systemLabels
(type:list(GoogleApi.Language.V1.Model.XPSMetricEntryLabel.t)
, default:nil
) - Billing system labels for this (metric, value) pair.
A single model artifact item.
Model evaluation metrics for regression problems. It can be used for Tables.
A pair of actual & observed values for the model being evaluated.
Attributes
-
effectiveTrainingDuration
(type:String.t
, default:nil
) - The effective time training used. If set, this is used for quota management and billing. Deprecated. AutoML BE doesn't use this. Don't set. -
metricEntries
(type:list(GoogleApi.Language.V1.Model.XPSMetricEntry.t)
, default:nil
) - One entry per metric name. The values must be aggregated per metric name.
Attributes
-
inputs
(type:%{optional(String.t) => GoogleApi.Language.V1.Model.XPSResponseExplanationMetadataInputMetadata.t}
, default:nil
) - Metadata of the input. -
outputs
(type:%{optional(String.t) => GoogleApi.Language.V1.Model.XPSResponseExplanationMetadataOutputMetadata.t}
, default:nil
) - Metadata of the output.
Metadata of the input of a feature.
Metadata of the prediction output to be explained.
Attributes
-
integratedGradientsAttribution
(type:GoogleApi.Language.V1.Model.XPSIntegratedGradientsAttribution.t
, default:nil
) - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 -
xraiAttribution
(type:GoogleApi.Language.V1.Model.XPSXraiAttribution.t
, default:nil
) - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
Specification of Model explanation. Feature-based XAI in AutoML Vision ICN is deprecated, see b/288407203 for context.
Attributes
-
columnIds
(type:list(integer())
, default:nil
) - The ids of the columns. Note: The belowvalues
field must match order of this field, if this field is set. -
values
(type:list(any())
, default:nil
) - The values of the row cells, given in the same order as the column_ids. If column_ids is not set, then in the same order as the input_feature_column_ids in TablesModelMetadata.
Attributes
-
biasingModelType
(type:String.t
, default:nil
) - Type of the biasing model. -
isEnhancedModel
(type:boolean()
, default:nil
) - If true then it means we have an enhanced version of the biasing models. -
numDeletions
(type:integer()
, default:nil
) - -
numInsertions
(type:integer()
, default:nil
) - -
numSubstitutions
(type:integer()
, default:nil
) - -
numUtterances
(type:integer()
, default:nil
) - Number of utterances used in the wer computation. -
numWords
(type:integer()
, default:nil
) - Number of words over which the word error rate was computed. -
sentenceAccuracy
(type:float()
, default:nil
) - Below fields are used for debugging purposes -
wer
(type:float()
, default:nil
) - Word error rate (standard error metric used for speech recognition).
Attributes
-
datasetId
(type:String.t
, default:nil
) - Required for speech xps backend. Speech xps has to use dataset_id and model_id as the primary key in db so that speech API can query the db directly. -
language
(type:String.t
, default:nil
) - -
subModelSpecs
(type:list(GoogleApi.Language.V1.Model.XPSSpeechModelSpecSubModelSpec.t)
, default:nil
) - Model specs for all submodels contained in this model.
Attributes
-
biasingModelType
(type:String.t
, default:nil
) - Type of the biasing model. -
clientId
(type:String.t
, default:nil
) - In S3, Recognition ClientContextId.client_id -
contextId
(type:String.t
, default:nil
) - In S3, Recognition ClientContextId.context_id -
isEnhancedModel
(type:boolean()
, default:nil
) - If true then it means we have an enhanced version of the biasing models.
Attributes
-
cnsTestDataPath
(type:String.t
, default:nil
) - Location od shards of sstables (test data) of DataUtterance protos. -
cnsTrainDataPath
(type:String.t
, default:nil
) - Location of shards of sstables (training data) of DataUtterance protos. -
prebuiltModelEvaluationMetrics
(type:GoogleApi.Language.V1.Model.XPSSpeechEvaluationMetrics.t
, default:nil
) - The metrics for prebuilt speech models. They are included here because there is no prebuilt speech models stored in the AutoML. -
speechPreprocessStats
(type:GoogleApi.Language.V1.Model.XPSSpeechPreprocessStats.t
, default:nil
) - Stats associated with the data.
Attributes
-
dataErrors
(type:list(GoogleApi.Language.V1.Model.XPSDataErrors.t)
, default:nil
) - Different types of data errors and the counts associated with them. -
numHumanLabeledExamples
(type:integer()
, default:nil
) - The number of rows marked HUMAN_LABELLED -
numLogsExamples
(type:integer()
, default:nil
) - The number of samples found in the previously recorded logs data. -
numMachineTranscribedExamples
(type:integer()
, default:nil
) - The number of rows marked as MACHINE_TRANSCRIBED -
testExamplesCount
(type:integer()
, default:nil
) - The number of examples labelled as TEST by Speech xps server. -
testSentencesCount
(type:integer()
, default:nil
) - The number of sentences in the test data set. -
testWordsCount
(type:integer()
, default:nil
) - The number of words in the test data set. -
trainExamplesCount
(type:integer()
, default:nil
) - The number of examples labeled as TRAIN by Speech xps server. -
trainSentencesCount
(type:integer()
, default:nil
) - The number of sentences in the training data set. -
trainWordsCount
(type:integer()
, default:nil
) - The number of words in the training data set.
The data statistics of a series of STRING values.
The statistics of a unigram.
The data statistics of a series of STRUCT values.
StructType
defines the DataType-s of a STRUCT type.
Attributes
-
columnSpecs
(type:%{optional(String.t) => GoogleApi.Language.V1.Model.XPSColumnSpec.t}
, default:nil
) - Mapping from column id to column spec. -
importedDataSizeInBytes
(type:String.t
, default:nil
) - The total size of imported data of the table. -
rowCount
(type:String.t
, default:nil
) - The number of rows in the table. -
timeColumnId
(type:integer()
, default:nil
) - The id of the time column. -
validRowCount
(type:String.t
, default:nil
) - The number of valid rows.
Metrics for Tables classification problems.
Metrics curve data point for a single value.
Metrics for a single confidence threshold.
Metadata for a dataset used for AutoML Tables. Next ID: 6
An information specific to given column and Tables Model, in context of the Model and the predictions created by it.
A description of Tables model structure.
Model hyper-parameters for a model.
Metrics for Tables regression problems.
Attributes
-
modelStructure
(type:GoogleApi.Language.V1.Model.XPSTablesModelStructure.t
, default:nil
) - -
predictionSampleRows
(type:list(GoogleApi.Language.V1.Model.XPSRow.t)
, default:nil
) - Sample rows from the dataset this model was trained. -
tablesModelColumnInfo
(type:list(GoogleApi.Language.V1.Model.XPSTablesModelColumnInfo.t)
, default:nil
) - Output only. Auxiliary information for each of the input_feature_column_specs, with respect to this particular model. -
trainCostMilliNodeHours
(type:String.t
, default:nil
) - The actual training cost of the model, expressed in milli node hours, i.e. 1,000 value in this field means 1 node hour. Guaranteed to not exceed the train budget.
Attributes
-
createModelStage
(type:String.t
, default:nil
) - Current stage of creating model. -
optimizationObjective
(type:String.t
, default:nil
) - The optimization objective for model. -
topTrials
(type:list(GoogleApi.Language.V1.Model.XPSTuningTrial.t)
, default:nil
) - This field is for training. When the operation is terminated successfully, AutoML Backend post this field to operation metadata in spanner. If the metadata has no trials returned, the training operation is supposed to be a failure. -
trainBudgetMilliNodeHours
(type:String.t
, default:nil
) - Creating model budget. -
trainingObjectivePoints
(type:list(GoogleApi.Language.V1.Model.XPSTrainingObjectivePoint.t)
, default:nil
) - This field records the training objective value with respect to time, giving insight into how the model architecture search is performing as training time elapses. -
trainingStartTime
(type:DateTime.t
, default:nil
) - Timestamp when training process starts.
Component model. Next ID: 10
Attributes
-
bestF1ConfidenceMetrics
(type:GoogleApi.Language.V1.Model.XPSConfidenceMetricsEntry.t
, default:nil
) - Values are at the highest F1 score on the precision-recall curve. Only confidence_threshold, recall, precision, and f1_score will be set. -
confidenceMetricsEntries
(type:list(GoogleApi.Language.V1.Model.XPSConfidenceMetricsEntry.t)
, default:nil
) - If the enclosing EvaluationMetrics.label is empty, confidence_metrics_entries is an evaluation of the entire model across all labels. If the enclosing EvaluationMetrics.label is set, confidence_metrics_entries applies to that label. -
confusionMatrix
(type:GoogleApi.Language.V1.Model.XPSConfusionMatrix.t
, default:nil
) - Confusion matrix of the model, at the default confidence threshold (0.0). Only set for whole-model evaluation, not for evaluation per label. -
perLabelConfidenceMetrics
(type:%{optional(String.t) => GoogleApi.Language.V1.Model.XPSConfidenceMetricsEntry.t}
, default:nil
) - Only recall, precision, and f1_score will be set.
Model evaluation metrics for text sentiment problems.
TextToSpeech train response
A TensorFlow.js model that can be used in the browser and in Node.js using JavaScript.
LINT.IfChange A model format used for mobile and IoT devices. See https://www.tensorflow.org/lite.
A tensorflow model format in SavedModel format.
The data statistics of a series of TIMESTAMP values.
Stats split by a defined in context granularity.
Track matching model metrics for a single track match threshold and multiple label match confidence thresholds. Next tag: 6.
Metrics for a single confidence threshold. Next tag: 6.
Next ID: 18
Evaluation metrics for the dataset.
Translation preprocess response.
Train response for translation.
Metrics for a tuning job generated, will get forwarded to Stackdriver as model tuning logs. Setting this as a standalone message out of CreateModelMetadata to avoid confusion as we expose this message only to users.
The Evaluation metrics entry given a specific precision_window_length.
Metrics for a single confidence threshold.
Model evaluation metrics for video action recognition.
Attributes
-
modelArtifactSpec
(type:GoogleApi.Language.V1.Model.XPSVideoModelArtifactSpec.t
, default:nil
) - ## The fields below are only populated under uCAIP request scope. -
trainCostNodeSeconds
(type:String.t
, default:nil
) - The actual train cost of creating this model, expressed in node seconds, i.e. 3,600 value in this field means 1 node hour.
Attributes
-
outputExamples
(type:list(String.t)
, default:nil
) - All the partial batch prediction results that are completed at the moment. Output examples are sorted by completion time. The order will not be changed. Each output example should be the path of a single RecordIO file of AnnotatedExamples.
Attributes
-
modelArtifactSpec
(type:GoogleApi.Language.V1.Model.XPSVideoModelArtifactSpec.t
, default:nil
) - ## The fields below are only populated under uCAIP request scope. -
trainCostNodeSeconds
(type:String.t
, default:nil
) - The actual train cost of creating this model, expressed in node seconds, i.e. 3,600 value in this field means 1 node hour.
Information of downloadable models that are pre-generated as part of training flow and will be persisted in AutoMl backend. Upon receiving ExportModel request from user, AutoMl backend can serve the pre-generated models to user if exists (by copying the files from internal path to user provided location), otherwise, AutoMl backend will call xPS ExportModel API to generate the model on the fly with the requesting format.
Attributes
-
exportArtifact
(type:list(GoogleApi.Language.V1.Model.XPSModelArtifactItem.t)
, default:nil
) - The model binary files in different formats for model export. -
servingArtifact
(type:GoogleApi.Language.V1.Model.XPSModelArtifactItem.t
, default:nil
) - The default model binary file used for serving (e.g. batch predict) via public Cloud AI Platform API.
Model evaluation metrics for ObjectTracking problems. Next tag: 10.
Attributes
-
exportModelSpec
(type:GoogleApi.Language.V1.Model.XPSVideoExportModelSpec.t
, default:nil
) - Populated for AutoML request only. -
modelArtifactSpec
(type:GoogleApi.Language.V1.Model.XPSVideoModelArtifactSpec.t
, default:nil
) - ## The fields below are only populated under uCAIP request scope. -
trainCostNodeSeconds
(type:String.t
, default:nil
) - The actual train cost of creating this model, expressed in node seconds, i.e. 3,600 value in this field means 1 node hour.
Attributes
-
trainCostMilliNodeHour
(type:String.t
, default:nil
) - This is an estimation of the node hours necessary for training a model, expressed in milli node hours (i.e. 1,000 value in this field means 1 node hour). A node hour represents the time a virtual machine spends running your training job. The cost of one node running for one hour is a node hour.
The vision model error analysis configuration. Next tag: 3
Visualization configurations for image explanation.
Attributes
-
exampleCount
(type:String.t
, default:nil
) - Optional. XPS server can opt to provide example count of the long running operation (e.g. training, data importing, batch prediction). -
reportingMetrics
(type:GoogleApi.Language.V1.Model.XPSReportingMetrics.t
, default:nil
) - Metrics for the operation. By the time the operation is terminated (whether succeeded or failed) as returned from XPS, AutoML BE assumes the metrics are finalized. AutoML BE transparently posts the metrics to Chemist if it's not empty, regardless of the response content or error type. If user is supposed to be charged in case of cancellation/error, this field should be set. In the case where the type of LRO doesn't require any billing, this field should be left unset. -
tablesTrainingOperationMetadata
(type:GoogleApi.Language.V1.Model.XPSTablesTrainingOperationMetadata.t
, default:nil
) - -
videoBatchPredictOperationMetadata
(type:GoogleApi.Language.V1.Model.XPSVideoBatchPredictOperationMetadata.t
, default:nil
) - -
videoTrainingOperationMetadata
(type:GoogleApi.Language.V1.Model.XPSVideoTrainingOperationMetadata.t
, default:nil
) - -
visionTrainingOperationMetadata
(type:GoogleApi.Language.V1.Model.XPSVisionTrainingOperationMetadata.t
, default:nil
) -
An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Only supports image Models (modality is IMAGE).
API client metadata for GoogleApi.Language.V2.
API calls for all endpoints tagged Documents
.
Handle Tesla connections for GoogleApi.Language.V2.
The entity analysis request message.
The entity analysis response message.
The sentiment analysis request message.
The sentiment analysis response message.
The request message for the text annotation API, which can perform multiple analysis types in one call.
All available features. Setting each one to true will enable that specific analysis for the input.
The text annotations response message.
Represents a category returned from the text classifier.
The document classification request message.
The document classification response message.
Represents a color in the RGBA color space. This representation is designed for simplicity of conversion to and from color representations in various languages over compactness. For example, the fields of this representation can be trivially provided to the constructor of java.awt.Color
in Java; it can also be trivially provided to UIColor's +colorWithRed:green:blue:alpha
method in iOS; and, with just a little work, it can be easily formatted into a CSS rgba()
string in JavaScript. This reference page doesn't have information about the absolute color space that should be used to interpret the RGB value—for example, sRGB, Adobe RGB, DCI-P3, and BT.2020. By default, applications should assume the sRGB color space. When color equality needs to be decided, implementations, unless documented otherwise, treat two colors as equal if all their red, green, blue, and alpha values each differ by at most 1e-5
. Example (Java): import com.google.type.Color; // ... public static java.awt.Color fromProto(Color protocolor) { float alpha = protocolor.hasAlpha() ? protocolor.getAlpha().getValue() : 1.0; return new java.awt.Color( protocolor.getRed(), protocolor.getGreen(), protocolor.getBlue(), alpha); } public static Color toProto(java.awt.Color color) { float red = (float) color.getRed(); float green = (float) color.getGreen(); float blue = (float) color.getBlue(); float denominator = 255.0; Color.Builder resultBuilder = Color .newBuilder() .setRed(red / denominator) .setGreen(green / denominator) .setBlue(blue / denominator); int alpha = color.getAlpha(); if (alpha != 255) { result.setAlpha( FloatValue .newBuilder() .setValue(((float) alpha) / denominator) .build()); } return resultBuilder.build(); } // ... Example (iOS / Obj-C): // ... static UIColor fromProto(Color protocolor) { float red = [protocolor red]; float green = [protocolor green]; float blue = [protocolor blue]; FloatValue alpha_wrapper = [protocolor alpha]; float alpha = 1.0; if (alpha_wrapper != nil) { alpha = [alpha_wrapper value]; } return [UIColor colorWithRed:red green:green blue:blue alpha:alpha]; } static Color toProto(UIColor color) { CGFloat red, green, blue, alpha; if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) { return nil; } Color result = [[Color alloc] init]; [result setRed:red]; [result setGreen:green]; [result setBlue:blue]; if (alpha <= 0.9999) { [result setAlpha:floatWrapperWithValue(alpha)]; } [result autorelease]; return result; } // ... Example (JavaScript): // ... var protoToCssColor = function(rgb_color) { var redFrac = rgb_color.red || 0.0; var greenFrac = rgb_color.green || 0.0; var blueFrac = rgb_color.blue || 0.0; var red = Math.floor(redFrac 255); var green = Math.floor(greenFrac 255); var blue = Math.floor(blueFrac * 255); if (!('alpha' in rgb_color)) { return rgbToCssColor(red, green, blue); } var alphaFrac = rgb_color.alpha.value || 0.0; var rgbParams = [red, green, blue].join(','); return ['rgba(', rgbParams, ',', alphaFrac, ')'].join(''); }; var rgbToCssColor = function(red, green, blue) { var rgbNumber = new Number((red << 16) | (green << 8) | blue); var hexString = rgbNumber.toString(16); var missingZeros = 6 - hexString.length; var resultBuilder = ['#']; for (var i = 0; i < missingZeros; i++) { resultBuilder.push('0'); } resultBuilder.push(hexString); return resultBuilder.join(''); }; // ...
Metric for billing reports.
Represents the input to API methods.
Represents a phrase in the text that is a known entity, such as a person, an organization, or location. The API associates information, such as probability and mentions, with entities.
Represents a mention for an entity in the text. Currently, proper noun mentions are supported.
Attributes
-
gpuSec
(type:String.t
, default:nil
) - Required. Seconds of GPU usage, e.g. 3600. -
gpuType
(type:String.t
, default:nil
) - Required. Type of GPU, e.g. NVIDIA_TESLA_V100. -
machineSpec
(type:String.t
, default:nil
) - Required. Machine spec, e.g. N1_STANDARD_4. -
trackingLabels
(type:map()
, default:nil
) - Billing tracking labels. They do not contain any user data but only the labels set by Vertex Core Infra itself. Tracking labels' keys are defined with special format: goog-[\p{Ll}\p{N}]+ E.g. "key": "goog-k8s-cluster-name","value": "us-east1-b4rk"
Infra Usage of billing metrics. Next ID: 6
The document moderation request message.
The document moderation response message.
Attributes
-
gibSec
(type:String.t
, default:nil
) - Required. VM memory in Gigabyte second, e.g. 3600. Using int64 type to match billing metrics definition. -
machineSpec
(type:String.t
, default:nil
) - Required. Machine spec, e.g. N1_STANDARD_4. -
memories
(type:float()
, default:nil
) - Required. VM memory in gb. -
ramType
(type:String.t
, default:nil
) - Required. Type of ram. -
trackingLabels
(type:map()
, default:nil
) - Billing tracking labels. They do not contain any user data but only the labels set by Vertex Core Infra itself. Tracking labels' keys are defined with special format: goog-[\p{Ll}\p{N}]+ E.g. "key": "goog-k8s-cluster-name","value": "us-east1-b4rk"
Represents a sentence in the input document.
Represents the feeling associated with the entire text or entities in the text.
The Status
type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC. Each Status
message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the API Design Guide.
Represents a text span in the input document.
The data statistics of a series of ARRAY values.
Bounding box matching model metrics for a single intersection-over-union threshold and multiple label match confidence thresholds.
Metrics for a single confidence threshold.
The data statistics of a series of CATEGORY values.
The statistics of a single CATEGORY value.
Model evaluation metrics for classification problems. It can be used for image and video classification. Next tag: 9.
Map from color to display name. Will only be used by Image Segmentation for uCAIP.
RGB color and each channel is represented by an integer.
Attributes
-
columnId
(type:integer()
, default:nil
) - The unique id of the column. When Preprocess, the Tables BE will popuate the order id of the column, which reflects the order of the column inside the table, i.e. 0 means the first column in the table, N-1 means the last column. AutoML BE will persist this order id in Spanner and set the order id here when calling RefreshTablesStats and Train. Note: it's different than the column_spec_id that is generated in AutoML BE. -
dataStats
(type:GoogleApi.Language.V2.Model.XPSDataStats.t
, default:nil
) - The data stats of the column. It's outputed in RefreshTablesStats and a required input for Train. -
dataType
(type:GoogleApi.Language.V2.Model.XPSDataType.t
, default:nil
) - The data type of the column. It's outputed in Preprocess rpc and a required input for RefreshTablesStats and Train. -
displayName
(type:String.t
, default:nil
) - The display name of the column. It's outputed in Preprocess and a required input for RefreshTablesStats and Train. -
forecastingMetadata
(type:GoogleApi.Language.V2.Model.XPSColumnSpecForecastingMetadata.t
, default:nil
) - -
topCorrelatedColumns
(type:list(GoogleApi.Language.V2.Model.XPSColumnSpecCorrelatedColumn.t)
, default:nil
) - It's outputed in RefreshTablesStats, and a required input in Train.
Identifies a table's column, and its correlation with the column this ColumnSpec describes.
=========================================================================== # The fields below are used exclusively for Forecasting.
Common statistics for a column with a specified data type.
ConfidenceMetricsEntry includes generic precision, recall, f1 score etc. Next tag: 16.
Confusion matrix of the model running the classification.
A row in the confusion matrix.
A model format used for iOS mobile devices.
A correlation statistics between two series of DataType values. The series may have differing DataType-s, but within a single series the DataType must be the same.
Different types of errors and the stats associatesd with each error.
The data statistics of a series of values that share the same DataType.
Indicated the type of data that can be stored in a structured data entity (e.g. a table).
A model format 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.
A model format used for Edge TPU devices.
Contains xPS-specific model evaluation metrics either for a single annotation spec (label), or for the model overall. Next tag: 18.
Specifies location of model evaluation metrics.
Set of examples or input sources.
Attributes
-
coreMlFormat
(type:GoogleApi.Language.V2.Model.XPSCoreMlFormat.t
, default:nil
) - -
dockerFormat
(type:GoogleApi.Language.V2.Model.XPSDockerFormat.t
, default:nil
) - -
edgeTpuTfLiteFormat
(type:GoogleApi.Language.V2.Model.XPSEdgeTpuTfLiteFormat.t
, default:nil
) - -
exportFirebaseAuxiliaryInfo
(type:boolean()
, default:nil
) - For any model and format: If true, will additionally export FirebaseExportedModelInfo in a firebase.txt file. -
outputGcrUri
(type:String.t
, default:nil
) - The Google Contained Registry (GCR) path the exported files to be pushed to. This location is set if the exported format is DOCKDER. -
outputGcsUri
(type:String.t
, default:nil
) - The Google Cloud Storage (GCS) directory where XPS will output the exported models and related files. Format: gs://bucket/directory -
tfJsFormat
(type:GoogleApi.Language.V2.Model.XPSTfJsFormat.t
, default:nil
) - -
tfLiteFormat
(type:GoogleApi.Language.V2.Model.XPSTfLiteFormat.t
, default:nil
) - -
tfSavedModelFormat
(type:GoogleApi.Language.V2.Model.XPSTfSavedModelFormat.t
, default:nil
) -
Spec of input and output files, on external file systems (CNS, GCS, etc).
The data statistics of a series of FLOAT64 values.
A bucket of a histogram.
Attributes
-
classCount
(type:String.t
, default:nil
) - Total number of classes. -
exportModelSpec
(type:GoogleApi.Language.V2.Model.XPSImageExportModelSpec.t
, default:nil
) - Information of downloadable models that are pre-generated as part of training flow and will be persisted in AutoMl backend. Populated for AutoMl requests. -
modelArtifactSpec
(type:GoogleApi.Language.V2.Model.XPSImageModelArtifactSpec.t
, default:nil
) - ## The fields below are only populated under uCAIP request scope. -
modelServingSpec
(type:GoogleApi.Language.V2.Model.XPSImageModelServingSpec.t
, default:nil
) - -
stopReason
(type:String.t
, default:nil
) - Stop reason for training job, e.g. 'TRAIN_BUDGET_REACHED', 'MODEL_CONVERGED', 'MODEL_EARLY_STOPPED'. -
trainCostInNodeTime
(type:String.t
, default:nil
) - The actual cost to create this model. - For edge type model, the cost is expressed in node hour. - For cloud type model,the cost is expressed in compute hour. - Populated for models created before GA. To be deprecated after GA. -
trainCostNodeSeconds
(type:String.t
, default:nil
) - The actual training cost, expressed in node seconds. Populated for models trained in node time.
Information of downloadable models that are pre-generated as part of training flow and will be persisted in AutoMl backend. Upon receiving ExportModel request from user, AutoMl backend can serve the pre-generated models to user if exists (by copying the files from internal path to user provided location), otherwise, AutoMl backend will call xPS ExportModel API to generate the model on the fly with the requesting format.
Stores the locations and related metadata of the model artifacts. Populated for uCAIP requests only.
Serving specification for image models.
Model evaluation metrics for image object detection problems. Evaluates prediction quality of labeled bounding boxes.
Attributes
-
classCount
(type:String.t
, default:nil
) - Total number of classes. -
exportModelSpec
(type:GoogleApi.Language.V2.Model.XPSImageExportModelSpec.t
, default:nil
) - -
maxBoundingBoxCount
(type:String.t
, default:nil
) - Max number of bounding box. -
modelArtifactSpec
(type:GoogleApi.Language.V2.Model.XPSImageModelArtifactSpec.t
, default:nil
) - ## The fields below are only populated under uCAIP request scope. -
modelServingSpec
(type:GoogleApi.Language.V2.Model.XPSImageModelServingSpec.t
, default:nil
) - -
stopReason
(type:String.t
, default:nil
) - Stop reason for training job, e.g. 'TRAIN_BUDGET_REACHED', 'MODEL_CONVERGED'. -
trainCostNodeSeconds
(type:String.t
, default:nil
) - The actual train cost of creating this model, expressed in node seconds, i.e. 3,600 value in this field means 1 node hour.
Model evaluation metrics for image segmentation problems. Next tag: 4.
Metrics for a single confidence threshold.
Attributes
-
colorMaps
(type:list(GoogleApi.Language.V2.Model.XPSColorMap.t)
, default:nil
) - Color map of the model. -
exportModelSpec
(type:GoogleApi.Language.V2.Model.XPSImageExportModelSpec.t
, default:nil
) - NOTE: These fields are not used/needed in EAP but will be set later. -
modelArtifactSpec
(type:GoogleApi.Language.V2.Model.XPSImageModelArtifactSpec.t
, default:nil
) - ## The fields below are only populated under uCAIP request scope. Model artifact spec stores and model gcs pathes and related metadata -
modelServingSpec
(type:GoogleApi.Language.V2.Model.XPSImageModelServingSpec.t
, default:nil
) - -
stopReason
(type:String.t
, default:nil
) - Stop reason for training job, e.g. 'TRAIN_BUDGET_REACHED', 'MODEL_CONVERGED'. -
trainCostNodeSeconds
(type:String.t
, default:nil
) - The actual train cost of creating this model, expressed in node seconds, i.e. 3,600 value in this field means 1 node hour.
An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
Attributes
-
argentumMetricId
(type:String.t
, default:nil
) - For billing metrics that are using legacy sku's, set the legacy billing metric id here. This will be sent to Chemist as the "cloudbilling.googleapis.com/argentum_metric_id" label. Otherwise leave empty. -
doubleValue
(type:float()
, default:nil
) - A double value. -
int64Value
(type:String.t
, default:nil
) - A signed 64-bit integer value. -
metricName
(type:String.t
, default:nil
) - The metric name defined in the service configuration. -
systemLabels
(type:list(GoogleApi.Language.V2.Model.XPSMetricEntryLabel.t)
, default:nil
) - Billing system labels for this (metric, value) pair.
A single model artifact item.
Model evaluation metrics for regression problems. It can be used for Tables.
A pair of actual & observed values for the model being evaluated.
Attributes
-
effectiveTrainingDuration
(type:String.t
, default:nil
) - The effective time training used. If set, this is used for quota management and billing. Deprecated. AutoML BE doesn't use this. Don't set. -
metricEntries
(type:list(GoogleApi.Language.V2.Model.XPSMetricEntry.t)
, default:nil
) - One entry per metric name. The values must be aggregated per metric name.
Attributes
-
inputs
(type:%{optional(String.t) => GoogleApi.Language.V2.Model.XPSResponseExplanationMetadataInputMetadata.t}
, default:nil
) - Metadata of the input. -
outputs
(type:%{optional(String.t) => GoogleApi.Language.V2.Model.XPSResponseExplanationMetadataOutputMetadata.t}
, default:nil
) - Metadata of the output.
Metadata of the input of a feature.
Metadata of the prediction output to be explained.
Attributes
-
integratedGradientsAttribution
(type:GoogleApi.Language.V2.Model.XPSIntegratedGradientsAttribution.t
, default:nil
) - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 -
xraiAttribution
(type:GoogleApi.Language.V2.Model.XPSXraiAttribution.t
, default:nil
) - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
Specification of Model explanation. Feature-based XAI in AutoML Vision ICN is deprecated, see b/288407203 for context.
Attributes
-
columnIds
(type:list(integer())
, default:nil
) - The ids of the columns. Note: The belowvalues
field must match order of this field, if this field is set. -
values
(type:list(any())
, default:nil
) - The values of the row cells, given in the same order as the column_ids. If column_ids is not set, then in the same order as the input_feature_column_ids in TablesModelMetadata.
Attributes
-
biasingModelType
(type:String.t
, default:nil
) - Type of the biasing model. -
isEnhancedModel
(type:boolean()
, default:nil
) - If true then it means we have an enhanced version of the biasing models. -
numDeletions
(type:integer()
, default:nil
) - -
numInsertions
(type:integer()
, default:nil
) - -
numSubstitutions
(type:integer()
, default:nil
) - -
numUtterances
(type:integer()
, default:nil
) - Number of utterances used in the wer computation. -
numWords
(type:integer()
, default:nil
) - Number of words over which the word error rate was computed. -
sentenceAccuracy
(type:float()
, default:nil
) - Below fields are used for debugging purposes -
wer
(type:float()
, default:nil
) - Word error rate (standard error metric used for speech recognition).
Attributes
-
datasetId
(type:String.t
, default:nil
) - Required for speech xps backend. Speech xps has to use dataset_id and model_id as the primary key in db so that speech API can query the db directly. -
language
(type:String.t
, default:nil
) - -
subModelSpecs
(type:list(GoogleApi.Language.V2.Model.XPSSpeechModelSpecSubModelSpec.t)
, default:nil
) - Model specs for all submodels contained in this model.
Attributes
-
biasingModelType
(type:String.t
, default:nil
) - Type of the biasing model. -
clientId
(type:String.t
, default:nil
) - In S3, Recognition ClientContextId.client_id -
contextId
(type:String.t
, default:nil
) - In S3, Recognition ClientContextId.context_id -
isEnhancedModel
(type:boolean()
, default:nil
) - If true then it means we have an enhanced version of the biasing models.
Attributes
-
cnsTestDataPath
(type:String.t
, default:nil
) - Location od shards of sstables (test data) of DataUtterance protos. -
cnsTrainDataPath
(type:String.t
, default:nil
) - Location of shards of sstables (training data) of DataUtterance protos. -
prebuiltModelEvaluationMetrics
(type:GoogleApi.Language.V2.Model.XPSSpeechEvaluationMetrics.t
, default:nil
) - The metrics for prebuilt speech models. They are included here because there is no prebuilt speech models stored in the AutoML. -
speechPreprocessStats
(type:GoogleApi.Language.V2.Model.XPSSpeechPreprocessStats.t
, default:nil
) - Stats associated with the data.
Attributes
-
dataErrors
(type:list(GoogleApi.Language.V2.Model.XPSDataErrors.t)
, default:nil
) - Different types of data errors and the counts associated with them. -
numHumanLabeledExamples
(type:integer()
, default:nil
) - The number of rows marked HUMAN_LABELLED -
numLogsExamples
(type:integer()
, default:nil
) - The number of samples found in the previously recorded logs data. -
numMachineTranscribedExamples
(type:integer()
, default:nil
) - The number of rows marked as MACHINE_TRANSCRIBED -
testExamplesCount
(type:integer()
, default:nil
) - The number of examples labelled as TEST by Speech xps server. -
testSentencesCount
(type:integer()
, default:nil
) - The number of sentences in the test data set. -
testWordsCount
(type:integer()
, default:nil
) - The number of words in the test data set. -
trainExamplesCount
(type:integer()
, default:nil
) - The number of examples labeled as TRAIN by Speech xps server. -
trainSentencesCount
(type:integer()
, default:nil
) - The number of sentences in the training data set. -
trainWordsCount
(type:integer()
, default:nil
) - The number of words in the training data set.
The data statistics of a series of STRING values.
The statistics of a unigram.
The data statistics of a series of STRUCT values.
StructType
defines the DataType-s of a STRUCT type.
Attributes
-
columnSpecs
(type:%{optional(String.t) => GoogleApi.Language.V2.Model.XPSColumnSpec.t}
, default:nil
) - Mapping from column id to column spec. -
importedDataSizeInBytes
(type:String.t
, default:nil
) - The total size of imported data of the table. -
rowCount
(type:String.t
, default:nil
) - The number of rows in the table. -
timeColumnId
(type:integer()
, default:nil
) - The id of the time column. -
validRowCount
(type:String.t
, default:nil
) - The number of valid rows.
Metrics for Tables classification problems.
Metrics curve data point for a single value.
Metrics for a single confidence threshold.
Metadata for a dataset used for AutoML Tables. Next ID: 6
An information specific to given column and Tables Model, in context of the Model and the predictions created by it.
A description of Tables model structure.
Model hyper-parameters for a model.
Metrics for Tables regression problems.
Attributes
-
modelStructure
(type:GoogleApi.Language.V2.Model.XPSTablesModelStructure.t
, default:nil
) - -
predictionSampleRows
(type:list(GoogleApi.Language.V2.Model.XPSRow.t)
, default:nil
) - Sample rows from the dataset this model was trained. -
tablesModelColumnInfo
(type:list(GoogleApi.Language.V2.Model.XPSTablesModelColumnInfo.t)
, default:nil
) - Output only. Auxiliary information for each of the input_feature_column_specs, with respect to this particular model. -
trainCostMilliNodeHours
(type:String.t
, default:nil
) - The actual training cost of the model, expressed in milli node hours, i.e. 1,000 value in this field means 1 node hour. Guaranteed to not exceed the train budget.
Attributes
-
createModelStage
(type:String.t
, default:nil
) - Current stage of creating model. -
optimizationObjective
(type:String.t
, default:nil
) - The optimization objective for model. -
topTrials
(type:list(GoogleApi.Language.V2.Model.XPSTuningTrial.t)
, default:nil
) - This field is for training. When the operation is terminated successfully, AutoML Backend post this field to operation metadata in spanner. If the metadata has no trials returned, the training operation is supposed to be a failure. -
trainBudgetMilliNodeHours
(type:String.t
, default:nil
) - Creating model budget. -
trainingObjectivePoints
(type:list(GoogleApi.Language.V2.Model.XPSTrainingObjectivePoint.t)
, default:nil
) - This field records the training objective value with respect to time, giving insight into how the model architecture search is performing as training time elapses. -
trainingStartTime
(type:DateTime.t
, default:nil
) - Timestamp when training process starts.
Component model. Next ID: 10
Attributes
-
bestF1ConfidenceMetrics
(type:GoogleApi.Language.V2.Model.XPSConfidenceMetricsEntry.t
, default:nil
) - Values are at the highest F1 score on the precision-recall curve. Only confidence_threshold, recall, precision, and f1_score will be set. -
confidenceMetricsEntries
(type:list(GoogleApi.Language.V2.Model.XPSConfidenceMetricsEntry.t)
, default:nil
) - If the enclosing EvaluationMetrics.label is empty, confidence_metrics_entries is an evaluation of the entire model across all labels. If the enclosing EvaluationMetrics.label is set, confidence_metrics_entries applies to that label. -
confusionMatrix
(type:GoogleApi.Language.V2.Model.XPSConfusionMatrix.t
, default:nil
) - Confusion matrix of the model, at the default confidence threshold (0.0). Only set for whole-model evaluation, not for evaluation per label. -
perLabelConfidenceMetrics
(type:%{optional(String.t) => GoogleApi.Language.V2.Model.XPSConfidenceMetricsEntry.t}
, default:nil
) - Only recall, precision, and f1_score will be set.
Model evaluation metrics for text sentiment problems.
TextToSpeech train response
A TensorFlow.js model that can be used in the browser and in Node.js using JavaScript.
LINT.IfChange A model format used for mobile and IoT devices. See https://www.tensorflow.org/lite.
A tensorflow model format in SavedModel format.
The data statistics of a series of TIMESTAMP values.
Stats split by a defined in context granularity.
Track matching model metrics for a single track match threshold and multiple label match confidence thresholds. Next tag: 6.
Metrics for a single confidence threshold. Next tag: 6.
Next ID: 18
Evaluation metrics for the dataset.
Translation preprocess response.
Train response for translation.
Metrics for a tuning job generated, will get forwarded to Stackdriver as model tuning logs. Setting this as a standalone message out of CreateModelMetadata to avoid confusion as we expose this message only to users.
The Evaluation metrics entry given a specific precision_window_length.
Metrics for a single confidence threshold.
Model evaluation metrics for video action recognition.
Attributes
-
modelArtifactSpec
(type:GoogleApi.Language.V2.Model.XPSVideoModelArtifactSpec.t
, default:nil
) - ## The fields below are only populated under uCAIP request scope. -
trainCostNodeSeconds
(type:String.t
, default:nil
) - The actual train cost of creating this model, expressed in node seconds, i.e. 3,600 value in this field means 1 node hour.
Attributes
-
outputExamples
(type:list(String.t)
, default:nil
) - All the partial batch prediction results that are completed at the moment. Output examples are sorted by completion time. The order will not be changed. Each output example should be the path of a single RecordIO file of AnnotatedExamples.
Attributes
-
modelArtifactSpec
(type:GoogleApi.Language.V2.Model.XPSVideoModelArtifactSpec.t
, default:nil
) - ## The fields below are only populated under uCAIP request scope. -
trainCostNodeSeconds
(type:String.t
, default:nil
) - The actual train cost of creating this model, expressed in node seconds, i.e. 3,600 value in this field means 1 node hour.
Information of downloadable models that are pre-generated as part of training flow and will be persisted in AutoMl backend. Upon receiving ExportModel request from user, AutoMl backend can serve the pre-generated models to user if exists (by copying the files from internal path to user provided location), otherwise, AutoMl backend will call xPS ExportModel API to generate the model on the fly with the requesting format.
Attributes
-
exportArtifact
(type:list(GoogleApi.Language.V2.Model.XPSModelArtifactItem.t)
, default:nil
) - The model binary files in different formats for model export. -
servingArtifact
(type:GoogleApi.Language.V2.Model.XPSModelArtifactItem.t
, default:nil
) - The default model binary file used for serving (e.g. batch predict) via public Cloud AI Platform API.
Model evaluation metrics for ObjectTracking problems. Next tag: 10.
Attributes
-
exportModelSpec
(type:GoogleApi.Language.V2.Model.XPSVideoExportModelSpec.t
, default:nil
) - Populated for AutoML request only. -
modelArtifactSpec
(type:GoogleApi.Language.V2.Model.XPSVideoModelArtifactSpec.t
, default:nil
) - ## The fields below are only populated under uCAIP request scope. -
trainCostNodeSeconds
(type:String.t
, default:nil
) - The actual train cost of creating this model, expressed in node seconds, i.e. 3,600 value in this field means 1 node hour.
Attributes
-
trainCostMilliNodeHour
(type:String.t
, default:nil
) - This is an estimation of the node hours necessary for training a model, expressed in milli node hours (i.e. 1,000 value in this field means 1 node hour). A node hour represents the time a virtual machine spends running your training job. The cost of one node running for one hour is a node hour.
The vision model error analysis configuration. Next tag: 3
Visualization configurations for image explanation.
Attributes
-
exampleCount
(type:String.t
, default:nil
) - Optional. XPS server can opt to provide example count of the long running operation (e.g. training, data importing, batch prediction). -
reportingMetrics
(type:GoogleApi.Language.V2.Model.XPSReportingMetrics.t
, default:nil
) - Metrics for the operation. By the time the operation is terminated (whether succeeded or failed) as returned from XPS, AutoML BE assumes the metrics are finalized. AutoML BE transparently posts the metrics to Chemist if it's not empty, regardless of the response content or error type. If user is supposed to be charged in case of cancellation/error, this field should be set. In the case where the type of LRO doesn't require any billing, this field should be left unset. -
tablesTrainingOperationMetadata
(type:GoogleApi.Language.V2.Model.XPSTablesTrainingOperationMetadata.t
, default:nil
) - -
videoBatchPredictOperationMetadata
(type:GoogleApi.Language.V2.Model.XPSVideoBatchPredictOperationMetadata.t
, default:nil
) - -
videoTrainingOperationMetadata
(type:GoogleApi.Language.V2.Model.XPSVideoTrainingOperationMetadata.t
, default:nil
) - -
visionTrainingOperationMetadata
(type:GoogleApi.Language.V2.Model.XPSVisionTrainingOperationMetadata.t
, default:nil
) -
An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Only supports image Models (modality is IMAGE).