{"id":37064856,"url":"https://github.com/aai-institute/nnbench","last_synced_at":"2026-01-14T07:35:12.683Z","repository":{"id":216789739,"uuid":"741902978","full_name":"aai-institute/nnbench","owner":"aai-institute","description":"A small framework for benchmarking machine learning models.","archived":false,"fork":false,"pushed_at":"2025-06-06T09:34:06.000Z","size":11129,"stargazers_count":20,"open_issues_count":6,"forks_count":3,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-09-14T09:51:33.429Z","etag":null,"topics":["benchmarking","machine-learning","mlops","neural-networks","python"],"latest_commit_sha":null,"homepage":"https://aai-institute.github.io/nnbench/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aai-institute.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-01-11T10:54:12.000Z","updated_at":"2025-09-04T15:24:18.000Z","dependencies_parsed_at":"2024-01-29T12:40:55.068Z","dependency_job_id":"4681242a-3c7b-43a5-86ba-c64307fefdc8","html_url":"https://github.com/aai-institute/nnbench","commit_stats":{"total_commits":153,"total_committers":4,"mean_commits":38.25,"dds":0.6013071895424836,"last_synced_commit":"ca30c5f090ff378c1cb050cf4e76fecca850060e"},"previous_names":["aai-institute/mlbench"],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/aai-institute/nnbench","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aai-institute%2Fnnbench","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aai-institute%2Fnnbench/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aai-institute%2Fnnbench/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aai-institute%2Fnnbench/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aai-institute","download_url":"https://codeload.github.com/aai-institute/nnbench/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aai-institute%2Fnnbench/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28413429,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-14T05:26:33.345Z","status":"ssl_error","status_checked_at":"2026-01-14T05:21:57.251Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["benchmarking","machine-learning","mlops","neural-networks","python"],"created_at":"2026-01-14T07:35:12.155Z","updated_at":"2026-01-14T07:35:12.674Z","avatar_url":"https://github.com/aai-institute.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# nnbench: A small framework for benchmarking machine learning models\n\nWelcome to nnbench, a framework for benchmarking machine learning models.\nThe main goals of this project are\n\n1. To provide a portable, easy-to-use solution for model evaluation that leads to better ML experiment organization, and\n2. To integrate with experiment and metadata tracking solutions for easy adoption.\n\nOn a high level, you can think of nnbench as \"pytest for ML models\" - you define benchmarks similarly to test cases, collect them, and selectively run them based on model type, markers, and environment info.\n\nWhat's new is that upon completion, you can stream the resulting data to any sink of your choice (including multiple at the same), which allows easy integration with experiment trackers and metadata stores.\n\nSee the [quickstart](https://aai-institute.github.io/nnbench/latest/quickstart/) for a lightning-quick demo, or the [examples](https://aai-institute.github.io/nnbench/latest/tutorials/) for more advanced usages.\n\n## Installation\n\n⚠️ nnbench is an experimental project - expect bugs and sharp edges.\n\nInstall it directly from source, for example either using `pip` or `uv`:\n\n```shell\npip install nnbench\n# or\nuv add nnbench\n```\n\n## A ⚡️- quick demo\n\nTo understand how nnbench works, you can run the following in your Python interpreter:\n\n```python\n# example.py\nimport nnbench\nfrom nnbench.reporter import ConsoleReporter\n\n\n@nnbench.benchmark\ndef product(a: int, b: int) -\u003e int:\n    return a * b\n\n\n@nnbench.benchmark\ndef power(a: int, b: int) -\u003e int:\n    return a ** b\n\n\nreporter = ConsoleReporter()\n# first, collect the above benchmarks directly from the current module...\nbenchmarks = nnbench.collect(\"__main__\")\n# ... then run the benchmarks with the parameters `a=2, b=10`...\nresult = nnbench.run(benchmarks, params={\"a\": 2, \"b\": 10})\nreporter.write(result)  # ...and print the results to the terminal.\n\n# results in a table look like the following:\n# ┏━━━━━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n# ┃ Benchmark ┃ Value ┃ Wall time (ns) ┃ Parameters        ┃\n# ┡━━━━━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n# │ product   │ 20    │ 1917           │ {'a': 2, 'b': 10} │\n# │ power     │ 1024  │ 583            │ {'a': 2, 'b': 10} │\n# └───────────┴───────┴────────────────┴───────────────────┘\n```\nWatch the following video for a high level overview of the capabilities and inner workings of nnbench.\n\n[![nnbench overview video thumbnail](https://img.youtube.com/vi/CT9bKq-U8ZQ/0.jpg)](https://www.youtube.com/watch?v=CT9bKq-U8ZQ)\n\nFor a more realistic example of how to evaluate a trained model with a benchmark suite, check the [Quickstart](https://aai-institute.github.io/nnbench/latest/quickstart/).\nFor even more advanced usages of the library, you can check out the [Examples](https://aai-institute.github.io/nnbench/latest/tutorials/) in the documentation.\n\n## Contributing\n\nWe encourage and welcome contributions from the community to enhance the project.\nPlease check [discussions](https://github.com/aai-institute/nnbench/discussions) or raise an [issue](https://github.com/aai-institute/nnbench/issues) on GitHub for any problems you encounter with the library.\n\nFor information on the general development workflow, see the [contribution guide](CONTRIBUTING.md).\n\n## License\n\nThe nnbench library is distributed under the [Apache-2 license](LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faai-institute%2Fnnbench","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faai-institute%2Fnnbench","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faai-institute%2Fnnbench/lists"}