TorchMetrics is a collection of 100+ PyTorch metrics implementations and an easy-to-use API to create custom metrics. It offers:
- A standardized interface to increase reproducibility
- Reduces Boilerplate
- Distributed-training compatible
- Rigorously tested
- Automatic accumulation over batches
- Automatic synchronization between multiple devices
You can use TorchMetrics in any PyTorch model, or within PyTorch Lightning to enjoy the following additional benefits:
- Your data will always be placed on the same device as your metrics
- You can log
~torchmetrics.Metric
objects directly in Lightning to reduce even more boilerplate
</div>
For pip users
pip install torchmetrics
Or directly from conda
conda install -c conda-forge torchmetrics
</div>
</div>
pages/quickstart all-metrics pages/overview pages/plotting pages/implement pages/lightning
aggregation/*
audio/*
classification/*
detection/*
image/*
multimodal/*
nominal/*
pairwise/*
regression/*
retrieval/*
text/*
wrappers/*
references/metric references/utilities
governance generated/CODE_OF_CONDUCT.md generated/CONTRIBUTING.md generated/CHANGELOG.md
genindex
modindex
search