RNNCell¶

class RNNCell(input_size, hidden_size, bias=True, nonlinearity='tanh')[源代码]¶

一个使用 tanh 或 ReLU 非线性的 Elman RNN 单元

\[h' = \tanh(W_{ih} x + b_{ih} + W_{hh} h + b_{hh})\]

如果 nonlinearity 是 ‘relu’ ，那么会使用 ReLU 代替 tanh。

参数

input_size (int) – The number of expected features in the input x.
hidden_size (int) – The number of features in the hidden state h.
bias (bool) – If False, then the layer does not use bias weights b_ih and b_hh. Default: True.
nonlinearity (str) – 需要使用的非线性函数。可以是 'tanh' 或 'relu' 。默认值： 'tanh'

形状：

输入：input，hidden
input: (batch, input_size). Tensor containing input features. hidden: (batch, hidden_size). Tensor containing the initial hidden state for each element in the batch. Defaults to zero if not provided.
输出： h’
h’: (batch, hidden_size). Tensor containing the next hidden state for each element in the batch.

实际案例

import numpy as np
import megengine as mge
import megengine.module as M

m = M.RNNCell(10, 20)
inp = mge.tensor(np.random.randn(3, 10), dtype=np.float32)
hx = mge.tensor(np.random.randn(3, 20), dtype=np.float32)
out = m(inp, hx)
print(out.numpy().shape)

输出：

(3, 20)

RNN

LSTM