{"adoption": {"forks": 83, "observed_at": "2026-08-28T04:03:57.834183+00:00", "stars": 1199}, "canonical_url": "https://ross.abutalabs.com/products/cleanvision", "card": {"archived": false, "artifact_type": "library", "description": "Automatically find issues in image datasets and practice data-centric computer vision.", "domain": ["computer-vision", "image-processing", "data-science", "machine-learning"], "enriched": true, "function": ["image-processing", "computer-vision", "data-science", "machine-learning"], "health_score": 73, "homepage": "https://cleanvision.readthedocs.io/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["cleanlab/cleanvision"], "name": "cleanlab/cleanvision", "platform": ["python", "cross-platform"], "pushed_at": "2026-01-08T07:19:58+00:00", "repo": "cleanlab/cleanvision", "stars": 1199, "tags": ["data-quality", "data-centric-ai", "image-deduplication", "dataset-audit", "exploratory-data-analysis"], "topics": ["computer-vision", "data-centric-ai", "data-exploration", "data-quality", "data-validation", "deep-learning", "exploratory-data-analysis", "image-analysis", "image-classification", "image-generation", "image-quality", "image-segmentation", "data-profiling", "data-science"], "urls": [], "use_cases": ["find blurry or low-quality images in my dataset", "detect near-duplicate images before training a model", "audit an image dataset for data quality issues", "check for dark or over-exposed images in a computer vision dataset", "clean up image data before training a classifier", "profile an image dataset for exploratory data analysis"], "what_it_is": "CleanVision is a Python library that automatically detects issues in image datasets, such as blurry, dark, over-exposed, or near-duplicate images. It provides a simple API to audit any image collection and generate a report before training machine learning models.", "when_to_avoid": ["you need image annotation or labeling tools", "you need general-purpose image editing or manipulation", "your data is not images (e.g., text or tabular data)"], "when_to_choose": ["you want a quick, automated first-pass quality check of an image dataset before ML training", "you need to find duplicates or low-quality images across a large folder of images with minimal code", "you follow a data-centric AI workflow and want dataset issue reports"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/cleanvision", "repo": "cleanlab/cleanvision", "role": "main", "score": 59}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.834183+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:20:52.642628+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87df2512d5d7be13e32d75fc88c60ef4d377fd921213c4e51f700a8b67b61256", "fetched_at": "2026-08-28T04:03:57.834183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanvision"}, {"content_hash": "22dc7448ee46bb0694434449c4e6f71eb7ab7e56fccc4ba3253ab2a4edd20b85", "fetched_at": "2026-08-29T12:28:57.456836+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanvision/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.834183+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:20:52.642628+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87df2512d5d7be13e32d75fc88c60ef4d377fd921213c4e51f700a8b67b61256", "fetched_at": "2026-08-28T04:03:57.834183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanvision"}, {"content_hash": "22dc7448ee46bb0694434449c4e6f71eb7ab7e56fccc4ba3253ab2a4edd20b85", "fetched_at": "2026-08-29T12:28:57.456836+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanvision/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:20:52.642628+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87df2512d5d7be13e32d75fc88c60ef4d377fd921213c4e51f700a8b67b61256", "fetched_at": "2026-08-28T04:03:57.834183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanvision"}, {"content_hash": "22dc7448ee46bb0694434449c4e6f71eb7ab7e56fccc4ba3253ab2a4edd20b85", "fetched_at": "2026-08-29T12:28:57.456836+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanvision/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.834183+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.834183+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.834183+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:20:52.642628+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87df2512d5d7be13e32d75fc88c60ef4d377fd921213c4e51f700a8b67b61256", "fetched_at": "2026-08-28T04:03:57.834183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanvision"}, {"content_hash": "22dc7448ee46bb0694434449c4e6f71eb7ab7e56fccc4ba3253ab2a4edd20b85", "fetched_at": "2026-08-29T12:28:57.456836+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanvision/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.834183+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.834183+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:20:52.642628+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87df2512d5d7be13e32d75fc88c60ef4d377fd921213c4e51f700a8b67b61256", "fetched_at": "2026-08-28T04:03:57.834183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanvision"}, {"content_hash": "22dc7448ee46bb0694434449c4e6f71eb7ab7e56fccc4ba3253ab2a4edd20b85", "fetched_at": "2026-08-29T12:28:57.456836+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanvision/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.834183+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.834183+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.834183+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:20:52.642628+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87df2512d5d7be13e32d75fc88c60ef4d377fd921213c4e51f700a8b67b61256", "fetched_at": "2026-08-28T04:03:57.834183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanvision"}, {"content_hash": "22dc7448ee46bb0694434449c4e6f71eb7ab7e56fccc4ba3253ab2a4edd20b85", "fetched_at": "2026-08-29T12:28:57.456836+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanvision/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.834183+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:57.834183+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:20:52.642628+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87df2512d5d7be13e32d75fc88c60ef4d377fd921213c4e51f700a8b67b61256", "fetched_at": "2026-08-28T04:03:57.834183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanvision"}, {"content_hash": "22dc7448ee46bb0694434449c4e6f71eb7ab7e56fccc4ba3253ab2a4edd20b85", "fetched_at": "2026-08-29T12:28:57.456836+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanvision/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:20:52.642628+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87df2512d5d7be13e32d75fc88c60ef4d377fd921213c4e51f700a8b67b61256", "fetched_at": "2026-08-28T04:03:57.834183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanvision"}, {"content_hash": "22dc7448ee46bb0694434449c4e6f71eb7ab7e56fccc4ba3253ab2a4edd20b85", "fetched_at": "2026-08-29T12:28:57.456836+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanvision/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:20:52.642628+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87df2512d5d7be13e32d75fc88c60ef4d377fd921213c4e51f700a8b67b61256", "fetched_at": "2026-08-28T04:03:57.834183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanvision"}, {"content_hash": "22dc7448ee46bb0694434449c4e6f71eb7ab7e56fccc4ba3253ab2a4edd20b85", "fetched_at": "2026-08-29T12:28:57.456836+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanvision/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:20:52.642628+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87df2512d5d7be13e32d75fc88c60ef4d377fd921213c4e51f700a8b67b61256", "fetched_at": "2026-08-28T04:03:57.834183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanvision"}, {"content_hash": "22dc7448ee46bb0694434449c4e6f71eb7ab7e56fccc4ba3253ab2a4edd20b85", "fetched_at": "2026-08-29T12:28:57.456836+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanvision/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 61, "longevity": 100, "rhythm": 32}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1560, "days_push": 237, "days_rel": 240, "gap_med": null, "n_releases_24m": 1}, "score": 59, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}