mirror of
https://github.com/pytorch/pytorch.git
synced 2026-11-20 09:04:25 +08:00
19da3da3d3
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
4.7 KiB
4.7 KiB
myst
| myst | ||||||
|---|---|---|---|---|---|---|
|
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: