Machine learning metrics for distributed, scalable PyTorch applications.
Lightning-AI/torchmetrics 的健康指数为 100 分中的 95 分,处于「卓越」区间。 其得分最高的类别是Engineering Quality(92/100),最低的是Security(63/100)。 最近一次更新在 2 天前。 近期的大部分工作由 2 位贡献者完成。
指标归入加权类别,统一采用 1–100 量表。总体分先取类别加权平均,再依据公开记录的分布进行校准,使各等级具有百分位含义;当公开证据触发高风险司法辖区政策时,评级会按政策调整,并设置 34(存在风险)的上限。
每条轴代表一个类别。形状比平均值更重要——健康的对象会填满整个图形,而“一峰一谷”式画像意味着某一维度的优势正掩盖另一维度的风险。
加权总体分 82 经校准后在公布的指数量表上为 95(记录校准 2026-08-02)。
| 注册表 | 软件包 | 版本 | 月下载量 | 版本数 | 最近发布 | 标签 |
|---|---|---|---|---|---|---|
| PyPI | torchmetrics | 1.9.0 | - | 73 | 130 天前 | deep-learningmachine-learningpytorchmetricsai |
项目是否仍有生命——是否仍在编写代码,是否仍在发布版本?
| 36/36 | 推送新近度 — 最近一次推送于 2 天前 |
| 17.3/36 | 提交节奏 — 52 周中有 25 周有提交 |
| 18/18 | 提交量 — 最近一年 110 次提交 |
| 10/10 | OpenSSF Scorecard:Maintained — 12 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| commits_last_year | 110 |
| human_commit_share | — |
| days_since_last_push | 2 |
| active_weeks_last_year | 25 |
| 27/27 | 有发布版本 — 已发布 65 个发布版本 |
| 27/36 | 发布时效 — 最近一次发布版本于 130 天前 |
| 27/27 | 发布节奏 — 约每 40 天发布一次 |
| 0/10 | OpenSSF Scorecard:Signed-Releases — Project has not signed or included provenance with any releases. |
| releases_count | 65 |
| latest_release_tag | v1.9.0 |
| releases_from_tags | 否 |
| days_since_latest_release | 130 |
| mean_days_between_releases | 40 |
项目是否拥有用户、下载量与关注度,并具备欢迎贡献者参与的配置?
| 55/60 | 星标 — 2,449 个星标 |
| 22.5/25 | 复刻 — 501 个复刻 |
| 7.8/15 | 关注者 — 26 位关注者 |
| forks | 501 |
| stars | 2,449 |
| watchers | 26 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
| 22.5/22.5 | README |
| 22.5/22.5 | 许可证 — 可识别的许可证(Apache-2.0) |
| 18/18 | CONTRIBUTING 指南 |
| 13.5/13.5 | 行为准则 |
| 0/7.2 | 议题模板 |
| 6.3/6.3 | PR 模板 |
| has_readme | 是 |
| has_license | 是 |
| readme_badges | — |
| has_contributing | 是 |
| has_issue_template | 否 |
| has_code_of_conduct | 是 |
| readme_badge_services | — |
| has_pull_request_template | 是 |
项目能否在其成员之外延续——巴士系数、响应能力、由谁支持,以及软件包的维护状况?
| 25.2/54 | 巴士系数 — 2 位贡献者贡献了半数提交 |
| 14.9/22.5 | 提交分布 — 头号贡献者编写了 34% 的提交 |
| 13.5/13.5 | 贡献者广度 — 100 位贡献者 |
| 10/10 | OpenSSF Scorecard:Contributors — project has 46 contributing companies or organizations |
| bus_factor | 2 |
| contributors_sampled | 100 |
| top_contributor_share | 0.336 |
| 38.3/42 | 议题解决 — 91% 的议题已关闭 |
| 27.2/30 | PR 接受 — 已裁定的 PR 中 1,911/2,109 已合并 |
| 0/13 | Newcomer PR acceptance — 30 天内没有首次贡献者的 PR 得到裁决 |
| 13.5/15 | OpenSSF Scorecard:Code-Review — Found 14/15 approved changesets -- score normalized to 9 |
| merged_prs | 1,911 |
| open_issues | 90 |
| closed_issues | 924 |
| prs_merged_7d | — |
| prs_decided_7d | — |
| prs_merged_30d | — |
| prs_decided_30d | — |
| issue_closed_ratio | 0.911 |
| closed_unmerged_prs | 198 |
| first_time_authors_30d | — |
| first_time_prs_merged_30d | — |
| first_time_prs_decided_30d | — |
| 30/30 | 所有权背书 — 组织持有 |
| 0/20 | 已验证域名 — 未读取该组织的域名验证状态 |
| 25/25 | 所有者影响力 — Lightning-AI 有 6,836 位关注者 |
| 22.8/25 | 既往记录 — 29 个公开仓库,账户约 6 年 |
| followers | 6,836 |
| owner_type | Organization |
| is_verified | — |
| owner_login | Lightning-AI |
| public_repos | 29 |
| account_age_days | 2,421 |
| 25/25 | 已发布且可解析 — pypi 上有 1 个软件包 |
| 35/35 | 发布时效 — 最近一次发布于 130 天前 |
| 20/20 | 版本历史 — 73 个已发布版本 |
| 20/20 | 未被弃用 — 活跃,未被弃用或撤回 |
| packages | torchmetrics |
| ecosystems | pypi |
| any_deprecated | 否 |
| min_days_since_publish | 130 |
基础的工程与文档实践是否到位?
| 24/24 | CI 工作流 — 12 个工作流 |
| 24/24 | 存在测试 |
| 16/16 | Linter 配置 |
| 9.6/9.6 | Pre-commit 钩子 |
| 0/6.4 | .editorconfig |
| 20/20 | OpenSSF Scorecard:CI-Tests — 30 out of 30 merged PRs checked by a CI test -- score normalized to 10 |
| has_ci | 是 |
| has_tests | 是 |
| has_editorconfig | 否 |
| has_linter_config | 是 |
| has_precommit_config | 是 |
| 30/30 | README |
| 25/25 | 文档目录 |
| 15/15 | 文档 / 主页站点 — https://lightning.ai/docs/torchmetrics/ |
| 10/10 | 仓库描述 |
| 10/10 | 主题标签 — 7 个主题标签 |
| 0/10 | Wiki |
| topics | python, data-science, machine-learning, pytorch, deep-learning, metrics, analyses |
| has_wiki | 否 |
| homepage | https://lightning.ai/docs/torchmetrics/ |
| docs_site | https://lightning.ai/docs/torchmetrics/ |
| has_readme | 是 |
| has_docs_dir | 是 |
| has_description | 是 |
可见的安全与供应链实践是否稳固,且不存在未解决的高风险司法辖区暴露?
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 0/7.5 | Branch-Protection — 无数据 |
| 2.5/2.5 | CI-Tests — 30 out of 30 merged PRs checked by a CI test -- score normalized to 10 |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 6.8/7.5 | Code-Review — Found 14/15 approved changesets -- score normalized to 9 |
| 2.5/2.5 | Contributors — project has 46 contributing companies or organizations |
| 10/10 | Dangerous-Workflow — no dangerous workflow patterns detected |
| 7.5/7.5 | Dependency-Update-Tool — update tool detected |
| 0/5 | Fuzzing — project is not fuzzed |
| 2.5/2.5 | 许可证 — license file detected |
| 7.5/7.5 | Maintained — 12 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| 5/5 | Packaging — packaging workflow detected |
| 4/5 | Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 8 |
| 0/5 | SAST — SAST tool is not run on all commits -- score normalized to 0 |
| 0/5 | Security-Policy — security policy file not detected |
| 0/7.5 | Signed-Releases — Project has not signed or included provenance with any releases. |
| 0/7.5 | Token-Permissions — detected GitHub workflow tokens with excessive permissions |
| 6/7.5 | Vulnerabilities — 2 existing vulnerabilities detected |
| source | openssf_scorecard |
| checks_evaluated | 17 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 1 |
| scorecard_aggregate | 6.3 |
该仓库在多大程度上具备与 AI 编码代理协同开发与维护的条件?权重刻意设小(4%):代理工具链是一项真实的维护信号,但完全不具备的仓库仍可达到 100/100。
| 0/45 | 代理指令 — 没有 CLAUDE.md / AGENTS.md / 编辑器规则 |
| 0/15 | 机器可读文档(llms.txt) |
| 0/40 | 可读的提交历史 — 无数据 |
| has_llms_txt | 否 |
| llms_txt_url | — |
| legible_history_share | — |
| agent_instruction_files | — |
| agent_instruction_max_bytes | — |
| 18/18 | 一条命令的引导启动 — Makefile, docs/Makefile |
| 22/22 | 自动化测试 |
| 11/11 | Lint / 格式化配置 |
| 11/11 | 静态类型检查 — src/torchmetrics/py.typed |
| 10/10 | 可复现环境 — devcontainer, Dockerfile |
| 0/10 | 已体现的代理实践 — 无数据 |
| 5/8 | 自动化维护 — 已配置依赖自动化,但在抽样提交中未观察到 |
| 8/10 | OpenSSF Scorecard:Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 8 |
| has_nix | 否 |
| has_tests | 是 |
| lockfiles | — |
| has_dockerfile | 是 |
| typed_language | 否 |
| bootstrap_files | Makefile, docs/Makefile |
| has_devcontainer | 是 |
| has_linter_config | 是 |
| typecheck_configs | src/torchmetrics/py.typed |
| agent_commit_share | — |
| toolchain_manifests | — |
| dependency_bot_commit_share | 0 |
| 27/45 | 可类型检查的代码 — Python,已配置类型检查(src/torchmetrics/py.typed) |
| 55/55 | 可控的文件大小 — 采样的 563 个源文件中有 0 个超过 60KB |
| primary_language | Python |
| largest_source_bytes | 57,049 |
| source_files_sampled | 563 |
| oversized_source_files | 0 |
| 0/40 | API 模式(OpenAPI/GraphQL/proto) — 不适用于此类软件 |
| 0/20 | MCP 服务器 — 不适用于此类软件 |
| 40/40 | 可运行示例 — examples |
| example_dirs | examples |
| has_mcp_signal | 否 |
| api_schema_files | — |
| interfaces_expected_of | — |
来自开源项目 OpenSSF Scorecard 的独立、工具无关的安全评估。每项检查奖励的是安全实践本身,而非特定供应商的工具。Scorecard 无法判定的检查项标记为 不适用,并从安全评分中剔除(绝不按零分计)。
| 10 | Binary-Artifacts | no binaries found in the repo |
| 不适用 | Branch-Protection | internal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md |
| 10 | CI-Tests | 30 out of 30 merged PRs checked by a CI test -- score normalized to 10 |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 9 | Code-Review | Found 14/15 approved changesets -- score normalized to 9 |
| 10 | Contributors | project has 46 contributing companies or organizations |
| 10 | Dangerous-Workflow | no dangerous workflow patterns detected |
| 10 | Dependency-Update-Tool | update tool detected |
| 0 | Fuzzing | project is not fuzzed |
| 10 | License | license file detected |
| 10 | Maintained | 12 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| 10 | Packaging | packaging workflow detected |
| 8 | Pinned-Dependencies | dependency not pinned by hash detected -- score normalized to 8 |
| 0 | SAST | SAST tool is not run on all commits -- score normalized to 0 |
| 0 | Security-Policy | security policy file not detected |
| 0 | Signed-Releases | Project has not signed or included provenance with any releases. |
| 0 | Token-Permissions | detected GitHub workflow tokens with excessive permissions |
| 8 | Vulnerabilities | 2 existing vulnerabilities detected |
来自 GitHub 依赖图的完整解析依赖集合:0 个直接依赖与 106 个间接(传递)软件包。仓库提交锁文件时,传递闭包才是完整的。
| 注册表 | 软件包 | 版本 | 关系 |
|---|---|---|---|
| PyPI | aeon | — | 间接 |
| PyPI | bert-score | 0.3.13 | 间接 |
| PyPI | cachier | 4.2.0 | 间接 |
| PyPI | cloudpickle | — | 间接 |
| PyPI | codecov | 2.1.13 | 间接 |
| PyPI | coverage | 7.10.7 | 间接 |
| PyPI | dists-pytorch | 0.1 | 间接 |
| PyPI | docutils | 0.19 | 间接 |
| PyPI | dython | 0.7.9 | 间接 |
| PyPI | einops | — | 间接 |
| PyPI | fairlearn | — | 间接 |
| PyPI | fast-bss-eval | — | 间接 |
| PyPI | faster-coco-eval | — | 间接 |
| PyPI | fire | — | 间接 |
| PyPI | gammatone | — | 间接 |
| PyPI | huggingface-hub | — | 间接 |
| PyPI | ipadic | — | 间接 |
| PyPI | ipython | — | 间接 |
| PyPI | jiwer | — | 间接 |
| PyPI | kornia | — | 间接 |
| PyPI | lai-sphinx-theme | — | 间接 |
| PyPI | librosa | — | 间接 |
| PyPI | lightning | — | 间接 |
| PyPI | lightning-utilities | — | 间接 |
| PyPI | lightning-utilities | 0.15.3 | 间接 |
| PyPI | lpips | — | 间接 |
| PyPI | matplotlib | — | 间接 |
| PyPI | mecab-ko | — | 间接 |
| PyPI | mecab-ko-dic | — | 间接 |
| PyPI | mecab-python3 | — | 间接 |
| PyPI | mir-eval | — | 间接 |
| PyPI | monai | 1.4.0 | 间接 |
| PyPI | mypy | 1.18.2 | 间接 |
| PyPI | myst-parser | 1.0.0 | 间接 |
| PyPI | netcal | — | 间接 |
| PyPI | nltk | — | 间接 |
| PyPI | numpy | — | 间接 |
| PyPI | onnxruntime | — | 间接 |
| PyPI | packaging | — | 间接 |
| PyPI | pandas | — | 间接 |
| PyPI | pandoc | 2.4 | 间接 |
| PyPI | permetrics | 2.0.0 | 间接 |
| PyPI | pesq | — | 间接 |
| PyPI | phmdoctest | 1.4.0 | 间接 |
| PyPI | piq | — | 间接 |
| PyPI | properscoring | 0.1 | 间接 |
| PyPI | psutil | — | 间接 |
| PyPI | py-tree | — | 间接 |
| PyPI | pycocotools | — | 间接 |
| PyPI | pydantic | — | 间接 |
| PyPI | pygithub | — | 间接 |
| PyPI | pystoi | — | 间接 |
| PyPI | pytdc | — | 间接 |
| PyPI | pytest | — | 间接 |
| PyPI | pytest | 8.4.2 | 间接 |
| PyPI | pytest-cov | 7.0.0 | 间接 |
| PyPI | pytest-doctestplus | — | 间接 |
| PyPI | pytest-doctestplus | 1.4.0 | 间接 |
| PyPI | pytest-rerunfailures | — | 间接 |
| PyPI | pytest-rerunfailures | 16.0.1 | 间接 |
| PyPI | pytest-timeout | 2.4.0 | 间接 |
| PyPI | pytest-xdist | 3.8.0 | 间接 |
| PyPI | pytorch-lightning | — | 间接 |
| PyPI | pytorch-msssim | 1.0.0 | 间接 |
| PyPI | regex | — | 间接 |
| PyPI | requests | — | 间接 |
| PyPI | rouge-score | — | 间接 |
| PyPI | sacrebleu | — | 间接 |
| PyPI | safetensors | — | 间接 |
| PyPI | scienceplots | — | 间接 |
| PyPI | scikit-image | — | 间接 |
| PyPI | scikit-learn | — | 间接 |
| PyPI | scipy | — | 间接 |
| PyPI | sentencepiece | — | 间接 |
| PyPI | setuptools | — | 间接 |
| PyPI | sewar | — | 间接 |
| PyPI | sphinx | 5.3.0 | 间接 |
| PyPI | sphinx-autobuild | 2024.10.3 | 间接 |
| PyPI | sphinx-autodoc-typehints | 1.23.0 | 间接 |
| PyPI | sphinx-copybutton | 0.5.2 | 间接 |
| PyPI | sphinx-gallery | 0.19.0 | 间接 |
| PyPI | sphinx-paramlinks | 0.6.0 | 间接 |
| PyPI | sphinx-togglebutton | 0.3.2 | 间接 |
| PyPI | sphinxcontrib-fulltoc | — | 间接 |
| PyPI | sphinxcontrib-mockautodoc | — | 间接 |
| PyPI | srmrpy | — | 间接 |
| PyPI | statsmodels | — | 间接 |
| PyPI | timm | — | 间接 |
| PyPI | torch | — | 间接 |
| PyPI | torch | 2.10.0 | 间接 |
| PyPI | torch-complex | — | 间接 |
| PyPI | torch-fidelity | — | 间接 |
| PyPI | torch-linear-assignment | — | 间接 |
| PyPI | torchaudio | — | 间接 |
| PyPI | torchvision | — | 间接 |
| PyPI | tqdm | — | 间接 |
| PyPI | transformers | — | 间接 |
| PyPI | types-emoji | — | 间接 |
| PyPI | types-protobuf | — | 间接 |
| PyPI | types-pyyaml | — | 间接 |
| PyPI | types-requests | — | 间接 |
| PyPI | types-setuptools | — | 间接 |
| PyPI | types-six | — | 间接 |
| PyPI | types-tabulate | — | 间接 |
| PyPI | vmaf-torch | — | 间接 |
| PyPI | wget | — | 间接 |
发现这份报告有不准确之处,或有想法要分享?错误的测量、未识别的工具、建议、疑问——都欢迎提出。每条消息都会被阅读并得到回复。