Struct InputMetadata 

#[non_exhaustive]
pub struct InputMetadata {
    pub input_baselines: Vec<Value>,
    pub input_tensor_name: String,
    pub encoding: Encoding,
    pub modality: String,
    pub feature_value_domain: Option<FeatureValueDomain>,
    pub indices_tensor_name: String,
    pub dense_shape_tensor_name: String,
    pub index_feature_mapping: Vec<String>,
    pub encoded_tensor_name: String,
    pub encoded_baselines: Vec<Value>,
    pub visualization: Option<Visualization>,
    pub group_name: String,
    /* private fields */
}

Available on crate features dataset-service or deployment-resource-pool-service or endpoint-service or job-service or model-service or pipeline-service only.

Metadata of the input of a feature.

Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

input_baselines: Vec<Value>

Baseline inputs for this feature.

If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions.

For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor.

For custom images, the element of the baselines must be in the same format as the feature’s input in the instance[]. The schema of any single instance may be specified via Endpoint’s DeployedModels’ Model’s PredictSchemata’s instance_schema_uri.

input_tensor_name: String

Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.

encoding: Encoding

Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.

modality: String

Modality of the feature. Valid values are: numeric, image. Defaults to numeric.

feature_value_domain: Option<FeatureValueDomain>

The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.

indices_tensor_name: String

Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.

dense_shape_tensor_name: String

Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.

index_feature_mapping: Vec<String>

A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.

encoded_tensor_name: String

Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable.

An encoded tensor is generated if the input tensor is encoded by a lookup table.

encoded_baselines: Vec<Value>

A list of baselines for the encoded tensor.

The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.

visualization: Option<Visualization>

Visualization configurations for image explanation.

group_name: String

Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.

Implementations

impl InputMetadata

pub fn new() -> Self

Creates a new default instance.

pub fn set_input_baselines<T, V>(self, v: T) -> Self

where T: IntoIterator<Item = V>, V: Into<Value>,

Sets the value of input_baselines.

Example

use wkt::Value;
let x = InputMetadata::new()
    .set_input_baselines([
        Value::default()/* use setters */,
        Value::default()/* use (different) setters */,
    ]);

pub fn set_input_tensor_name<T: Into<String>>(self, v: T) -> Self

Sets the value of input_tensor_name.

Example

let x = InputMetadata::new().set_input_tensor_name("example");

pub fn set_encoding<T: Into<Encoding>>(self, v: T) -> Self

Sets the value of encoding.

Example

use google_cloud_aiplatform_v1::model::explanation_metadata::input_metadata::Encoding;
let x0 = InputMetadata::new().set_encoding(Encoding::Identity);
let x1 = InputMetadata::new().set_encoding(Encoding::BagOfFeatures);
let x2 = InputMetadata::new().set_encoding(Encoding::BagOfFeaturesSparse);

pub fn set_modality<T: Into<String>>(self, v: T) -> Self

Sets the value of modality.

Example

let x = InputMetadata::new().set_modality("example");

pub fn set_feature_value_domain<T>(self, v: T) -> Self

where T: Into<FeatureValueDomain>,

Sets the value of feature_value_domain.

Example

use google_cloud_aiplatform_v1::model::explanation_metadata::input_metadata::FeatureValueDomain;
let x = InputMetadata::new().set_feature_value_domain(FeatureValueDomain::default()/* use setters */);

pub fn set_or_clear_feature_value_domain<T>(self, v: Option<T>) -> Self

where T: Into<FeatureValueDomain>,

Sets or clears the value of feature_value_domain.

Example

use google_cloud_aiplatform_v1::model::explanation_metadata::input_metadata::FeatureValueDomain;
let x = InputMetadata::new().set_or_clear_feature_value_domain(Some(FeatureValueDomain::default()/* use setters */));
let x = InputMetadata::new().set_or_clear_feature_value_domain(None::<FeatureValueDomain>);

pub fn set_indices_tensor_name<T: Into<String>>(self, v: T) -> Self

Sets the value of indices_tensor_name.

Example

let x = InputMetadata::new().set_indices_tensor_name("example");

pub fn set_dense_shape_tensor_name<T: Into<String>>(self, v: T) -> Self

Sets the value of dense_shape_tensor_name.

Example

let x = InputMetadata::new().set_dense_shape_tensor_name("example");

pub fn set_index_feature_mapping<T, V>(self, v: T) -> Self

where T: IntoIterator<Item = V>, V: Into<String>,

Sets the value of index_feature_mapping.

Example

let x = InputMetadata::new().set_index_feature_mapping(["a", "b", "c"]);

pub fn set_encoded_tensor_name<T: Into<String>>(self, v: T) -> Self

Sets the value of encoded_tensor_name.

Example

let x = InputMetadata::new().set_encoded_tensor_name("example");

pub fn set_encoded_baselines<T, V>(self, v: T) -> Self

where T: IntoIterator<Item = V>, V: Into<Value>,

Sets the value of encoded_baselines.

Example

use wkt::Value;
let x = InputMetadata::new()
    .set_encoded_baselines([
        Value::default()/* use setters */,
        Value::default()/* use (different) setters */,
    ]);

pub fn set_visualization<T>(self, v: T) -> Self

where T: Into<Visualization>,

Sets the value of visualization.

Example

use google_cloud_aiplatform_v1::model::explanation_metadata::input_metadata::Visualization;
let x = InputMetadata::new().set_visualization(Visualization::default()/* use setters */);

pub fn set_or_clear_visualization<T>(self, v: Option<T>) -> Self

where T: Into<Visualization>,

Sets or clears the value of visualization.

Example

use google_cloud_aiplatform_v1::model::explanation_metadata::input_metadata::Visualization;
let x = InputMetadata::new().set_or_clear_visualization(Some(Visualization::default()/* use setters */));
let x = InputMetadata::new().set_or_clear_visualization(None::<Visualization>);

pub fn set_group_name<T: Into<String>>(self, v: T) -> Self

Sets the value of group_name.

Example

let x = InputMetadata::new().set_group_name("example");

Trait Implementations

impl Clone for InputMetadata

fn clone(&self) -> InputMetadata

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for InputMetadata

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for InputMetadata

fn default() -> InputMetadata

Returns the “default value” for a type.

impl Message for InputMetadata

fn typename() -> &'static str

The typename of this message.

impl PartialEq for InputMetadata

fn eq(&self, other: &InputMetadata) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for InputMetadata