torch_npu.contrib.BiLSTM

API接口

torch_npu.contrib.BiLSTM(input_size, hidden_size)

功能描述

将NPU兼容的双向LSTM操作应用于输入序列。

参数说明

• input_size：The number of expected features in the input `x`
• hidden_size：The number of features in the hidden state `h`

示例

    >>> r = BiLSTM(512, 256)
    >>> input_tensor = torch.randn(26, 2560, 512)
    >>> output = r(input_tensor)