{"adoption": {"forks": 376, "observed_at": "2026-08-28T04:08:50.346193+00:00", "stars": 4443}, "canonical_url": "https://ross.abutalabs.com/products/img2dataset", "card": {"archived": false, "artifact_type": "cli-tool", "description": "Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.", "domain": ["machine-learning", "computer-vision", "big-data"], "enriched": true, "function": ["image-processing", "etl", "data-generation"], "health_score": 63, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["rom1504/img2dataset"], "name": "rom1504/img2dataset", "platform": ["python", "cli", "windows"], "pushed_at": "2025-10-19T21:22:50+00:00", "repo": "rom1504/img2dataset", "stars": 4443, "tags": ["image-dataset", "webdataset", "image-download", "multimodal", "url-to-dataset", "resizer", "data-engineering", "linux", "macos"], "topics": ["deep-learning", "dataset", "big-data", "image", "multimodal", "image-dataset", "download-images"], "urls": [], "use_cases": ["download images from a list of urls into a dataset", "build an image-text dataset for training models", "download and resize millions of images quickly", "create a laion-style dataset from image url list", "package image urls into webdataset shards", "download mscoco or cc3m image datasets"], "what_it_is": "A Python tool that downloads large sets of image URLs and packages them into machine learning datasets, with resizing and caption support. It can process 100M URLs in 20 hours on a single machine and powers datasets like LAION-5B.", "when_to_avoid": ["you only need a handful of images and a simple downloader suffices", "you need to scrape and discover image urls rather than download from an existing list", "you need dataset labeling or annotation, not downloading"], "when_to_choose": ["you need to turn a large url list into a usable image dataset at scale", "you want image+caption pairs for training multimodal models", "you need fast, parallel, resumable image downloading with resizing"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/img2dataset", "repo": "rom1504/img2dataset", "role": "main", "score": 56}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.346193+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:20:49.144601+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "045b437a77bea1b64d68480af0f90c903863a2f5872d9f5bf44162a3bb0b0613", "fetched_at": "2026-08-28T04:08:50.346193+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rom1504/img2dataset"}, {"content_hash": "cfb7594006706b9c9edf6870496ad8b906d402d5724fe0f1db875c87b2c07bd6", "fetched_at": "2026-08-29T09:07:51.766729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/img2dataset/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.346193+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:20:49.144601+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "045b437a77bea1b64d68480af0f90c903863a2f5872d9f5bf44162a3bb0b0613", "fetched_at": "2026-08-28T04:08:50.346193+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rom1504/img2dataset"}, {"content_hash": "cfb7594006706b9c9edf6870496ad8b906d402d5724fe0f1db875c87b2c07bd6", "fetched_at": "2026-08-29T09:07:51.766729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/img2dataset/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:20:49.144601+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "045b437a77bea1b64d68480af0f90c903863a2f5872d9f5bf44162a3bb0b0613", "fetched_at": "2026-08-28T04:08:50.346193+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rom1504/img2dataset"}, {"content_hash": "cfb7594006706b9c9edf6870496ad8b906d402d5724fe0f1db875c87b2c07bd6", "fetched_at": "2026-08-29T09:07:51.766729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/img2dataset/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.346193+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.346193+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.346193+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:20:49.144601+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "045b437a77bea1b64d68480af0f90c903863a2f5872d9f5bf44162a3bb0b0613", "fetched_at": "2026-08-28T04:08:50.346193+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rom1504/img2dataset"}, {"content_hash": "cfb7594006706b9c9edf6870496ad8b906d402d5724fe0f1db875c87b2c07bd6", "fetched_at": "2026-08-29T09:07:51.766729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/img2dataset/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.346193+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.346193+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:20:49.144601+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "045b437a77bea1b64d68480af0f90c903863a2f5872d9f5bf44162a3bb0b0613", "fetched_at": "2026-08-28T04:08:50.346193+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rom1504/img2dataset"}, {"content_hash": "cfb7594006706b9c9edf6870496ad8b906d402d5724fe0f1db875c87b2c07bd6", "fetched_at": "2026-08-29T09:07:51.766729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/img2dataset/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.346193+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.346193+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.346193+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:20:49.144601+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "045b437a77bea1b64d68480af0f90c903863a2f5872d9f5bf44162a3bb0b0613", "fetched_at": "2026-08-28T04:08:50.346193+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rom1504/img2dataset"}, {"content_hash": "cfb7594006706b9c9edf6870496ad8b906d402d5724fe0f1db875c87b2c07bd6", "fetched_at": "2026-08-29T09:07:51.766729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/img2dataset/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.346193+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.346193+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:20:49.144601+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "045b437a77bea1b64d68480af0f90c903863a2f5872d9f5bf44162a3bb0b0613", "fetched_at": "2026-08-28T04:08:50.346193+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rom1504/img2dataset"}, {"content_hash": "cfb7594006706b9c9edf6870496ad8b906d402d5724fe0f1db875c87b2c07bd6", "fetched_at": "2026-08-29T09:07:51.766729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/img2dataset/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:20:49.144601+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "045b437a77bea1b64d68480af0f90c903863a2f5872d9f5bf44162a3bb0b0613", "fetched_at": "2026-08-28T04:08:50.346193+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rom1504/img2dataset"}, {"content_hash": "cfb7594006706b9c9edf6870496ad8b906d402d5724fe0f1db875c87b2c07bd6", "fetched_at": "2026-08-29T09:07:51.766729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/img2dataset/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:20:49.144601+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "045b437a77bea1b64d68480af0f90c903863a2f5872d9f5bf44162a3bb0b0613", "fetched_at": "2026-08-28T04:08:50.346193+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rom1504/img2dataset"}, {"content_hash": "cfb7594006706b9c9edf6870496ad8b906d402d5724fe0f1db875c87b2c07bd6", "fetched_at": "2026-08-29T09:07:51.766729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/img2dataset/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:20:49.144601+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "045b437a77bea1b64d68480af0f90c903863a2f5872d9f5bf44162a3bb0b0613", "fetched_at": "2026-08-28T04:08:50.346193+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rom1504/img2dataset"}, {"content_hash": "cfb7594006706b9c9edf6870496ad8b906d402d5724fe0f1db875c87b2c07bd6", "fetched_at": "2026-08-29T09:07:51.766729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/img2dataset/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 47, "longevity": 100, "rhythm": 42}, "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": 1848, "days_push": 318, "days_rel": 389, "gap_med": 0, "n_releases_24m": 2}, "score": 56, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}