ngraph.opset4.embedding_bag_offsets_sum(emb_table: _pyngraph.Node, indices: Union[_pyngraph.Node, int, float, numpy.ndarray], offsets: Union[_pyngraph.Node, int, float, numpy.ndarray], default_index: Optional[Union[_pyngraph.Node, int, float, numpy.ndarray]] = None, per_sample_weights: Optional[Union[_pyngraph.Node, int, float, numpy.ndarray]] = None, name: Optional[str] = None)_pyngraph.Node

Return a node which performs sums of bags of embeddings without the intermediate embeddings.

  • emb_table – Tensor containing the embedding lookup table.

  • indices – Tensor with indices.

  • offsets – Tensor containing the starting index positions of each bag in indices.

  • per_sample_weights – Tensor with weights for each sample.

  • default_index – Scalar containing default index in embedding table to fill empty bags.

  • name – Optional name for output node.


The new node which performs EmbeddingBagOffsetsSum