tflite_support.task.processor.FeatureVector

A dense feature vector.

tflite_support.task.processor.FeatureVector(
    value: np.ndarray
)

Only one of the two fields is ever present. Feature vectors are assumed to be one-dimensional and L2-normalized.

value A NumPy array indidcating the raw output of the embedding layer. The datatype of elements in the array can be either float or uint8 if quantize is set to True in EmbeddingOptions.

Methods

create_from_pb2

View source

@classmethod
create_from_pb2(
    pb2_obj: _FeatureVectorProto
) -> 'FeatureVector'

Creates a FeatureVector object from the given protobuf object.

to_pb2

View source

to_pb2() -> _FeatureVectorProto

Generates a protobuf object to pass to the C++ layer.

__eq__

View source

__eq__(
    other: Any
) -> bool

Checks if this object is equal to the given object.

Args
other The object to be compared with.

Returns
True if the objects are equal.