RNNCell — PyTorch 2.7 documentation (original) (raw)

class torch.nn.RNNCell(input_size, hidden_size, bias=True, nonlinearity='tanh', device=None, dtype=None)[source][source]¶

An Elman RNN cell with tanh or ReLU non-linearity.

h′=tanh⁡(Wihx+bih+Whhh+bhh)h' = \tanh(W_{ih} x + b_{ih} + W_{hh} h + b_{hh})

If nonlinearity is ‘relu’, then ReLU is used in place of tanh.

Parameters

• 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) – The non-linearity to use. Can be either 'tanh' or 'relu'. Default: 'tanh'

Inputs: input, hidden

• input: tensor containing input features
• hidden: tensor containing the initial hidden state Defaults to zero if not provided.

Outputs: h’

• h’ of shape (batch, hidden_size): tensor containing the next hidden state for each element in the batch

Shape:

• input: (N,Hin)(N, H_{in}) or (Hin)(H_{in}) tensor containing input features whereHinH_{in} = input_size.
• hidden: (N,Hout)(N, H_{out}) or (Hout)(H_{out}) tensor containing the initial hidden state where HoutH_{out} = hidden_size. Defaults to zero if not provided.
• output: (N,Hout)(N, H_{out}) or (Hout)(H_{out}) tensor containing the next hidden state.

Variables

• weight_ih (torch.Tensor) – the learnable input-hidden weights, of shape(hidden_size, input_size)
• weight_hh (torch.Tensor) – the learnable hidden-hidden weights, of shape(hidden_size, hidden_size)
• bias_ih – the learnable input-hidden bias, of shape (hidden_size)
• bias_hh – the learnable hidden-hidden bias, of shape (hidden_size)

Note

All the weights and biases are initialized from U(−k,k)\mathcal{U}(-\sqrt{k}, \sqrt{k})where k=1hidden_sizek = \frac{1}{\text{hidden\_size}}

Examples:

rnn = nn.RNNCell(10, 20) input = torch.randn(6, 3, 10) hx = torch.randn(3, 20) output = [] for i in range(6): ... hx = rnn(input[i], hx) ... output.append(hx)