RNNCell#

classtorch.nn.modules.rnn.RNNCell(input_size,hidden_size,bias=True,nonlinearity='tanh',device=None,dtype=None)[source]#

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

$$h^{\mathrm{\prime }}=\tanh (W_{ih}x+b_{ih}+W_{hh}h+b_{hh})$$h′=tanh(Wih​x+bih​+Whh​h+bhh​)

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

Parameters

• input_size (int) – The number of expected features in the inputx

• hidden_size (int) – The number of features in the hidden stateh

• bias (bool) – IfFalse, then the layer does not use bias weightsb_ih andb_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 stateDefaults to zero if not provided.

Outputs: h’

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

Shape:

• input:$(N,H_{in})$(N,Hin​) or$(H_{in})$(Hin​) tensor containing input features where$H_{in}$Hin​ =input_size.

• hidden:$(N,H_{out})$(N,Hout​) or$(H_{out})$(Hout​) tensor containing the initial hiddenstate where$H_{out}$Hout​ =hidden_size. Defaults to zero if not provided.

• output:$(N,H_{out})$(N,Hout​) or$(H_{out})$(Hout​) 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$\mathcal{U}(-\sqrt{k},\sqrt{k})$U(−k​,k​)where$k=\frac{1}{\text{hidden\_size}}$k=hidden_size1​

Examples:

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