Files
pytorch/docs/cpp/source/api/nn/loss.md
T
Svetlana Karslioglu 19da3da3d3 Restructure C++ docs (#174096)
The fix-cpp-build branch is a major restructuring that:

- Drops Exhale (which auto-generated API docs but caused OOM in CI) in favor of hand-written RST pages using Breathe directives
- Reorganizes notes into a hierarchical API reference with proper categories
- Adds new content: XPU docs, stable ABI docs, DeviceGuard/Stream docs
- Always runs Doxygen instead of gating on an env var

Pull Request resolved: https://github.com/pytorch/pytorch/pull/174096
Approved by: https://github.com/janeyx99, https://github.com/seemethere, https://github.com/albanD
2026-04-07 17:24:38 +00:00

4.7 KiB

myst
myst
html_meta
description keywords
Loss functions in PyTorch C++ — CrossEntropyLoss, MSELoss, NLLLoss, BCELoss, and more. PyTorch, C++, loss, CrossEntropyLoss, MSELoss, NLLLoss, BCELoss, L1Loss

Loss Functions

Loss functions measure how well the model's predictions match the targets. The choice of loss function depends on your task type and data characteristics.

Regression losses:

  • L1Loss/MSELoss: Basic regression losses (MAE vs MSE)
  • SmoothL1Loss/HuberLoss: Robust to outliers

Classification losses:

  • CrossEntropyLoss: Multi-class classification (combines LogSoftmax + NLLLoss)
  • NLLLoss: Negative log likelihood (use with LogSoftmax output)
  • BCELoss/BCEWithLogitsLoss: Binary classification

Specialized losses:

  • CTCLoss: Sequence-to-sequence without alignment (speech recognition)
  • TripletMarginLoss: Metric learning (similarity/embedding tasks)
  • CosineEmbeddingLoss: Similarity learning with cosine distance

L1Loss

:members:
:undoc-members:
:members:
:undoc-members:

MSELoss

:members:
:undoc-members:
:members:
:undoc-members:

Example:

auto loss_fn = torch::nn::MSELoss();
auto loss = loss_fn->forward(predictions, targets);

CrossEntropyLoss

:members:
:undoc-members:
:members:
:undoc-members:

Example:

auto loss_fn = torch::nn::CrossEntropyLoss();
auto logits = torch::randn({32, 10});  // [batch, num_classes]
auto targets = torch::randint(0, 10, {32});  // [batch]
auto loss = loss_fn->forward(logits, targets);

NLLLoss

:members:
:undoc-members:
:members:
:undoc-members:

BCELoss

:members:
:undoc-members:
:members:
:undoc-members:

BCEWithLogitsLoss

:members:
:undoc-members:
:members:
:undoc-members:

HuberLoss

:members:
:undoc-members:
:members:
:undoc-members:

SmoothL1Loss

:members:
:undoc-members:
:members:
:undoc-members:

KLDivLoss

:members:
:undoc-members:
:members:
:undoc-members:

CTCLoss

:members:
:undoc-members:
:members:
:undoc-members:

PoissonNLLLoss

:members:
:undoc-members:
:members:
:undoc-members:

MarginRankingLoss

:members:
:undoc-members:
:members:
:undoc-members:

HingeEmbeddingLoss

:members:
:undoc-members:
:members:
:undoc-members:

CosineEmbeddingLoss

:members:
:undoc-members:
:members:
:undoc-members:

MultiMarginLoss

:members:
:undoc-members:
:members:
:undoc-members:

MultiLabelMarginLoss

:members:
:undoc-members:
:members:
:undoc-members:

MultiLabelSoftMarginLoss

:members:
:undoc-members:
:members:
:undoc-members:

SoftMarginLoss

:members:
:undoc-members:
:members:
:undoc-members:

TripletMarginLoss

:members:
:undoc-members:
:members:
:undoc-members:

TripletMarginWithDistanceLoss

:members:
:undoc-members:
:members:
:undoc-members: