mp.tasks.components.containers.Embedding

Embedding result for a given embedder head.

Main aliases

mp.tasks.components.containers.Embedding(
    embedding: np.ndarray,
    head_index: Optional[int] = None,
    head_name: Optional[str] = None
)

Attributes
`embedding`	The actual embedding, either floating-point or scalar-quantized.
`head_index`	The index of the embedder head that produced this embedding. This is useful for multi-head models.
`head_name`	The name of the embedder head, which is the corresponding tensor metadata name (if any). This is useful for multi-head models.

Methods

@classmethod
create_from_pb2(
    pb2_obj: mp.tasks.components.utils.cosine_similarity.embedding_result.embeddings_pb2.Embedding
) -> 'Embedding'

Creates a Embedding object from the given protobuf object.

__eq__(
    other
)

Class Variables
head_index	`None`
head_name	`None`