Linear Layers

Linear layers apply affine transformations to input data: y = xW^T + b. They are the building blocks of fully-connected networks and are used for feature transformation, classification heads, and projection layers.

Linear: Standard fully-connected layer
Bilinear: Bilinear transformation of two inputs
Identity: Pass-through layer (useful for skip connections)
Flatten/Unflatten: Reshape tensors between convolutional and linear layers

Linear

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

Example:

cpp

auto linear = torch::nn::Linear(torch::nn::LinearOptions(784, 256).bias(true));
auto output = linear->forward(input);  // input: [N, 784]

Bilinear

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

Identity

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

Flatten

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

Unflatten

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members: