DynSeqOuter

Description

Sums up by offset.

Input

• x1: input tensor of type float16 or float, with a shape of [bs, feature_dim]. bs indicates the number of data records in a batch, and feature_dim indicates the feature dimension.
• x2: input tensor of type float16 or float, with a shape of [bs, feature_dim]. bs indicates the number of data records in a batch, and feature_dim indicates the feature dimension.
• seq_len1: tensor of type int32, with shape [batch_size] and bs=sum (seq_len1).
• seq_len2: tensor of type int32, with shape [batch_size] and bs=sum (seq_len2).

Output

y: output tensor of type float16 or float, with shape [bs, feature_dim] and bs=sum(seq_len1 * seq_len2).

Constraints

This operator is customized for specific user scenarios. You are advised not to use this operator in irrelevant scenarios.

ONNX Opset Support

Opset v8/v9/v10/v11/v12/v13/v14/v15/v16