# torchmetrics > PyTorch native Metrics - **URL**: https://www.freshcrate.ai/projects/torchmetrics - **Author**: Lightning-AI et al. - **Category**: Developer Tools - **Latest version**: `1.9.0` (2026-04-21) - **License**: Apache-2.0 - **Source**: https://github.com/Lightning-AI/torchmetrics/issues - **Homepage**: https://github.com/Lightning-AI/torchmetrics - **Language**: Python - **GitHub**: 2,429 stars, 485 forks - **Registry**: pypi (`torchmetrics`) - **Tags**: `ai`, `deep`, `learning`, `machine`, `metrics`, `pypi`, `pytorch` ## Description
**Machine learning metrics for distributed, scalable PyTorch applications.** ______________________________________________________________________

What is Torchmetrics • Implementing a metric • Built-in metrics • Docs • Community • License

______________________________________________________________________ [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/torchmetrics)](https://pypi.org/project/torchmetrics/) [![PyPI Status](https://badge.fury.io/py/torchmetrics.svg)](https://badge.fury.io/py/torchmetrics) [![PyPI - Downloads](https://img.shields.io/pypi/dm/torchmetrics) ](https://pepy.tech/project/torchmetrics) [![Conda](https://img.shields.io/conda/v/conda-forge/torchmetrics?label=conda&color=success)](https://anaconda.org/conda-forge/torchmetrics) [![license](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/Lightning-AI/torchmetrics/blob/master/LICENSE) [![CI testing | CPU](https://github.com/Lightning-AI/torchmetrics/actions/workflows/ci-tests.yml/badge.svg?event=push)](https://github.com/Lightning-AI/torchmetrics/actions/workflows/ci-tests.yml) [![Build Status](https://dev.azure.com/Lightning-AI/Metrics/_apis/build/status%2FTM.unittests?branchName=refs%2Ftags%2Fv1.9.0)](https://dev.azure.com/Lightning-AI/Metrics/_build/latest?definitionId=2&branchName=refs%2Ftags%2Fv1.9.0) [![codecov](https://codecov.io/gh/Lightning-AI/torchmetrics/release/v1.9.0/graph/badge.svg?token=NER6LPI3HS)](https://codecov.io/gh/Lightning-AI/torchmetrics) [![pre-commit.ci status](https://results.pre-commit.ci/badge/github/Lightning-AI/torchmetrics/master.svg)](https://results.pre-commit.ci/latest/github/Lightning-AI/torchmetrics/master) [![Documentation Status](https://readthedocs.org/projects/torchmetrics/badge/?version=latest)](https://torchmetrics.readthedocs.io/en/latest/?badge=latest) [![Discord](https://img.shields.io/discord/1077906959069626439?style=plastic)](https://discord.gg/VptPCZkGNa) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5844769.svg)](https://doi.org/10.5281/zenodo.5844769) [![JOSS status](https://joss.theoj.org/papers/561d9bb59b400158bc8204e2639dca43/status.svg)](https://joss.theoj.org/papers/561d9bb59b400158bc8204e2639dca43) ______________________________________________________________________
# Looking for GPUs? Over 340,000 developers use [Lightning Cloud](https://lightning.ai/?utm_source=tm_readme&utm_medium=referral&utm_campaign=tm_readme) - purpose-built for PyTorch and PyTorch Lightning. - [GPUs](https://lightning.ai/pricing?utm_source=tm_readme&utm_medium=referral&utm_campaign=tm_readme) from $0.19. - [Clusters](https://lightning.ai/clusters?utm_source=tm_readme&utm_medium=referral&utm_campaign=tm_readme): frontier-grade training/inference clusters. - [AI Studio (vibe train)](https://lightning.ai/studios?utm_source=tm_readme&utm_medium=referral&utm_campaign=tm_readme): workspaces where AI helps you debug, tune and vibe train. - [AI Studio (vibe deploy)](https://lightning.ai/studios?utm_source=tm_readme&utm_medium=referral&utm_campaign=tm_readme): workspaces where AI helps you optimize, and deploy models. - [Notebooks](https://lightning.ai/notebooks?utm_source=tm_readme&utm_medium=referral&utm_campaign=tm_readme): Persistent GPU workspaces where AI helps you code and analyze. - [Inference](https://lightning.ai/deploy?utm_source=tm_readme&utm_medium=referral&utm_campaign=tm_readme): Deploy models as inference APIs. # Installation Simple installation from PyPI ```bash pip install torchmetrics ```
Other installations Install using conda ```bash conda install -c conda-forge torchmetrics ``` Install using uv ```bash uv add torchmetrics ``` Pip from source ```bash # with git pip install git+https://github.com/Lightning-AI/torchmetrics.git@release/stable ``` Pip from archive ```bash pip install https://github.com/Lightning-AI/torchmetrics/archive/refs/heads/release/stable.zip ``` Extra dependencies for specialized metrics: ```bash pip install torchmetrics[audio] pip install torchmetrics[image] pip install torchmetrics[text] pip install torchmetrics[all] # install all of the above ``` Install latest developer version ```bash pip install https://github.com/Lightning-AI/torchmetrics/archive/master.zip ```
______________________________________________________________________ # What is TorchMetrics 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 reproducibili ## Recent releases | Version | Date | Urgency | Changes | | --- | --- | --- | --- | | `1.9.0` | 2026-04-21 | Low | Imported from PyPI (1.9.0) | | `v1.9.0` | 2026-03-09 | Low | ## [1.9.0] - 2026-03-06 ### Changed - Defaulting Dice score `average="macro"` ([#3042](https://github.com/Lightning-AI/torchmetrics/pull/3042)) - Dropped Python 3.9 support, set 3.10 as minimum ([#3330](https://github.com/Lightning-AI/torchmetrics/pull/3330)) - Replaced `pkg_resources` with `packaging` ([#3329](https://github.com/Lightning-AI/torchmetrics/pull/3329)) ### Fixed - Fixed device mismatch in `Metric` base class ([#3316](https://github.com/Lightning-AI/torchmetrics/pull/ | | `v1.9.0` | 2026-03-09 | Low | ## [1.9.0] - 2026-03-06 ### Changed - Defaulting Dice score `average="macro"` ([#3042](https://github.com/Lightning-AI/torchmetrics/pull/3042)) - Dropped Python 3.9 support, set 3.10 as minimum ([#3330](https://github.com/Lightning-AI/torchmetrics/pull/3330)) - Replaced `pkg_resources` with `packaging` ([#3329](https://github.com/Lightning-AI/torchmetrics/pull/3329)) ### Fixed - Fixed device mismatch in `Metric` base class ([#3316](https://github.com/Lightning-AI/torchmetrics/pull/ | | `v1.9.0` | 2026-03-09 | Low | ## [1.9.0] - 2026-03-06 ### Changed - Defaulting Dice score `average="macro"` ([#3042](https://github.com/Lightning-AI/torchmetrics/pull/3042)) - Dropped Python 3.9 support, set 3.10 as minimum ([#3330](https://github.com/Lightning-AI/torchmetrics/pull/3330)) - Replaced `pkg_resources` with `packaging` ([#3329](https://github.com/Lightning-AI/torchmetrics/pull/3329)) ### Fixed - Fixed device mismatch in `Metric` base class ([#3316](https://github.com/Lightning-AI/torchmetrics/pull/ | | `v1.9.0` | 2026-03-09 | Low | ## [1.9.0] - 2026-03-06 ### Changed - Defaulting Dice score `average="macro"` ([#3042](https://github.com/Lightning-AI/torchmetrics/pull/3042)) - Dropped Python 3.9 support, set 3.10 as minimum ([#3330](https://github.com/Lightning-AI/torchmetrics/pull/3330)) - Replaced `pkg_resources` with `packaging` ([#3329](https://github.com/Lightning-AI/torchmetrics/pull/3329)) ### Fixed - Fixed device mismatch in `Metric` base class ([#3316](https://github.com/Lightning-AI/torchmetrics/pull/ | | `v1.9.0` | 2026-03-09 | Low | ## [1.9.0] - 2026-03-06 ### Changed - Defaulting Dice score `average="macro"` ([#3042](https://github.com/Lightning-AI/torchmetrics/pull/3042)) - Dropped Python 3.9 support, set 3.10 as minimum ([#3330](https://github.com/Lightning-AI/torchmetrics/pull/3330)) - Replaced `pkg_resources` with `packaging` ([#3329](https://github.com/Lightning-AI/torchmetrics/pull/3329)) ### Fixed - Fixed device mismatch in `Metric` base class ([#3316](https://github.com/Lightning-AI/torchmetrics/pull/ | | `v1.9.0` | 2026-03-09 | Low | ## [1.9.0] - 2026-03-06 ### Changed - Defaulting Dice score `average="macro"` ([#3042](https://github.com/Lightning-AI/torchmetrics/pull/3042)) - Dropped Python 3.9 support, set 3.10 as minimum ([#3330](https://github.com/Lightning-AI/torchmetrics/pull/3330)) - Replaced `pkg_resources` with `packaging` ([#3329](https://github.com/Lightning-AI/torchmetrics/pull/3329)) ### Fixed - Fixed device mismatch in `Metric` base class ([#3316](https://github.com/Lightning-AI/torchmetrics/pull/ | | `v1.9.0` | 2026-03-09 | Low | ## [1.9.0] - 2026-03-06 ### Changed - Defaulting Dice score `average="macro"` ([#3042](https://github.com/Lightning-AI/torchmetrics/pull/3042)) - Dropped Python 3.9 support, set 3.10 as minimum ([#3330](https://github.com/Lightning-AI/torchmetrics/pull/3330)) - Replaced `pkg_resources` with `packaging` ([#3329](https://github.com/Lightning-AI/torchmetrics/pull/3329)) ### Fixed - Fixed device mismatch in `Metric` base class ([#3316](https://github.com/Lightning-AI/torchmetrics/pull/ | | `v1.9.0` | 2026-03-09 | Low | ## [1.9.0] - 2026-03-06 ### Changed - Defaulting Dice score `average="macro"` ([#3042](https://github.com/Lightning-AI/torchmetrics/pull/3042)) - Dropped Python 3.9 support, set 3.10 as minimum ([#3330](https://github.com/Lightning-AI/torchmetrics/pull/3330)) - Replaced `pkg_resources` with `packaging` ([#3329](https://github.com/Lightning-AI/torchmetrics/pull/3329)) ### Fixed - Fixed device mismatch in `Metric` base class ([#3316](https://github.com/Lightning-AI/torchmetrics/pull/ | | `v1.9.0` | 2026-03-09 | Low | ## [1.9.0] - 2026-03-06 ### Changed - Defaulting Dice score `average="macro"` ([#3042](https://github.com/Lightning-AI/torchmetrics/pull/3042)) - Dropped Python 3.9 support, set 3.10 as minimum ([#3330](https://github.com/Lightning-AI/torchmetrics/pull/3330)) - Replaced `pkg_resources` with `packaging` ([#3329](https://github.com/Lightning-AI/torchmetrics/pull/3329)) ### Fixed - Fixed device mismatch in `Metric` base class ([#3316](https://github.com/Lightning-AI/torchmetrics/pull/ | ## Citation - HTML: https://www.freshcrate.ai/projects/torchmetrics - Markdown: https://www.freshcrate.ai/projects/torchmetrics.md - Dependencies JSON: https://www.freshcrate.ai/api/projects/torchmetrics/deps _Generated by freshcrate.ai. Indexes pypi releases for AI-agent ecosystem packages._