LSTMP

Description

Computes a one-layer LSTMP.

Input

Five to eight inputs:

x: tensor of type float16.

wx: tensor of type float16.

bias: tensor of type float16.

wr: tensor of type float16.

project: tensor of type float16.

real_mask: (optional) tensor of type float16.

init_h: (optional) tensor of type float16.

init_c: (optional) tensor of type float16.

Output

Three outputs:

y: tensor of type float16.

output_h: tensor of type float16.

output_c: tensor of type float16.

Constraints

This operator is customized for specific user scenarios and is not recommended in irrelevant scenarios.

ONNX Opset Support

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