Google Cloud Ai Platform V1 Client - Class Encoding (0.10.0)

Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class Encoding.

Defines how a feature is encoded. Defaults to IDENTITY.

Protobuf type google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.Encoding

Methods

name

Parameter
NameDescription
value mixed

value

Parameter
NameDescription
name mixed

Constants

ENCODING_UNSPECIFIED

Value: 0

Default value. This is the same as IDENTITY.

Generated from protobuf enum ENCODING_UNSPECIFIED = 0;

IDENTITY

Value: 1

The tensor represents one feature.

Generated from protobuf enum IDENTITY = 1;

BAG_OF_FEATURES

Value: 2

The tensor represents a bag of features where each index maps to a feature. InputMetadata.index_feature_mapping must be provided for this encoding. For example:

input = [27, 6.0, 150]
index_feature_mapping = ["age", "height", "weight"]

Generated from protobuf enum BAG_OF_FEATURES = 2;

BAG_OF_FEATURES_SPARSE

Value: 3

The tensor represents a bag of features where each index maps to a feature. Zero values in the tensor indicates feature being non-existent. InputMetadata.index_feature_mapping must be provided for this encoding. For example:

input = [2, 0, 5, 0, 1]
index_feature_mapping = ["a", "b", "c", "d", "e"]

Generated from protobuf enum BAG_OF_FEATURES_SPARSE = 3;

INDICATOR

Value: 4

The tensor is a list of binaries representing whether a feature exists or not (1 indicates existence). InputMetadata.index_feature_mapping must be provided for this encoding. For example:

input = [1, 0, 1, 0, 1]
index_feature_mapping = ["a", "b", "c", "d", "e"]

Generated from protobuf enum INDICATOR = 4;

COMBINED_EMBEDDING

Value: 5

The tensor is encoded into a 1-dimensional array represented by an encoded tensor. InputMetadata.encoded_tensor_name must be provided for this encoding. For example:

input = ["This", "is", "a", "test", "."]
encoded = [0.1, 0.2, 0.3, 0.4, 0.5]

Generated from protobuf enum COMBINED_EMBEDDING = 5;

CONCAT_EMBEDDING

Value: 6

Select this encoding when the input tensor is encoded into a 2-dimensional array represented by an encoded tensor.

InputMetadata.encoded_tensor_name must be provided for this encoding. The first dimension of the encoded tensor's shape is the same as the input tensor's shape. For example:

input = ["This", "is", "a", "test", "."]
encoded = [[0.1, 0.2, 0.3, 0.4, 0.5],
           [0.2, 0.1, 0.4, 0.3, 0.5],
           [0.5, 0.1, 0.3, 0.5, 0.4],
           [0.5, 0.3, 0.1, 0.2, 0.4],
           [0.4, 0.3, 0.2, 0.5, 0.1]]

Generated from protobuf enum CONCAT_EMBEDDING = 6;