Linear#

classtorch.nn.Linear(in_features,out_features,bias=True,device=None,dtype=None)[source]#

Applies an affine linear transformation to the incoming data:$y=x{A}^T+b$y=xAT+b.

This module supportsTensorFloat32.

On certain ROCm devices, when using float16 inputs this module will usedifferent precision for backward.

Parameters

• in_features (int) – size of each input sample

• out_features (int) – size of each output sample

• bias (bool) – If set toFalse, the layer will not learn an additive bias.Default:True

Shape:

• Input:$(\ast ,H_{\text{in}})$(∗,Hin​) where$\ast$∗ means any number ofdimensions including none and$H_{\text{in}}=\text{in\_features}$Hin​=in_features.

• Output:$(\ast ,H_{\text{out}})$(∗,Hout​) where all but the last dimensionare the same shape as the input and$H_{\text{out}}=\text{out\_features}$Hout​=out_features.

Variables

• weight (torch.Tensor) – the learnable weights of the module of shape$(\text{out\_features},\text{in\_features})$(out_features,in_features). The values areinitialized from$\mathcal{U}(-\sqrt{k},\sqrt{k})$U(−k​,k​), where$k=\frac{1}{\text{in\_features}}$k=in_features1​

• bias – the learnable bias of the module of shape$(\text{out\_features})$(out_features).Ifbias isTrue, the values are initialized from$\mathcal{U}(-\sqrt{k},\sqrt{k})$U(−k​,k​) where$k=\frac{1}{\text{in\_features}}$k=in_features1​

Examples:

>>>m=nn.Linear(20,30)>>>input=torch.randn(128,20)>>>output=m(input)>>>print(output.size())torch.Size([128, 30])

extra_repr()[source]#

Return the extra representation of the module.

Return type

str

forward(input)[source]#

Runs the forward pass.

Return type

Tensor

reset_parameters()[source]#

Resets parameters based on their initialization used in__init__.