pytorch/docs/cpp/source/api/nn/functional.md

myst

myst
html_meta description keywords Functional API in PyTorch C++ — torch::nn::functional stateless operations for neural networks. PyTorch, C++, functional, torch::nn::functional, relu, conv2d, linear, softmax

Functional API

The torch::nn::functional namespace provides stateless versions of neural network operations. Unlike module classes, functional operations do not hold learnable parameters — you pass weights explicitly.

When to use functional vs modules:

• Use modules (torch::nn::Conv2d) when you need learnable parameters managed automatically (training, saving, loading).
• Use functional (torch::nn::functional::conv2d) when you already have weights as tensors, or for operations without parameters (e.g., relu).

#include <torch/nn/functional.h>
namespace F = torch::nn::functional;

// Stateless activation — no module needed
auto output = F::relu(input);

// Convolution with explicit weight tensor
auto output = F::conv2d(input, weight, F::Conv2dFuncOptions().stride(1).padding(1));

// Softmax along a dimension
auto probs = F::softmax(logits, F::SoftmaxFuncOptions(/*dim=*/1));

Activation Functions

Convolution Functions

Pooling Functions

Linear Functions

Dropout Functions

Embedding Functions

Normalization Functions

Loss Functions

Distance Functions

Vision Functions

Fold/Unfold

Functional Options Structs

Each functional operation that takes configuration uses a corresponding options struct. The naming convention is <Operation>FuncOptions.

Activation Options:

Convolution Options:

Pooling Options:

Other Options: