{"adoption": {"forks": 315, "observed_at": "2026-08-28T04:07:30.986876+00:00", "stars": 2939}, "canonical_url": "https://ross.abutalabs.com/products/table-transformer", "card": {"archived": false, "artifact_type": "library", "description": "Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS evaluation metric.", "domain": ["computer-vision", "pdf", "machine-learning", "data-science"], "enriched": true, "function": ["machine-learning", "computer-vision", "ocr", "pdf", "image-processing", "parser"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["microsoft/table-transformer"], "name": "microsoft/table-transformer", "platform": ["python", "cross-platform"], "pushed_at": "2024-06-24T13:41:20+00:00", "repo": "microsoft/table-transformer", "stars": 2939, "tags": ["table-detection", "table-structure-recognition", "object-detection", "pubtables-1m", "grits", "document-understanding", "pytorch", "natural-language-processing"], "topics": ["table-detection", "table-extraction", "table-structure-recognition", "table-functional-analysis"], "urls": [], "use_cases": ["extract tables from pdf documents", "detect tables in scanned images", "convert table images to html or csv", "recognize table structure in unstructured documents", "train a custom table extraction model", "evaluate table structure recognition models with grits", "download pubtables-1m dataset for research"], "what_it_is": "Table Transformer (TATR) is a deep learning object detection model from Microsoft for detecting, recognizing, and extracting tables from unstructured documents like PDFs and images, outputting HTML or CSV. It is also the official repository for the PubTables-1M dataset and the GriTS evaluation metric.", "when_to_avoid": ["you need a turnkey end-to-end document parser with OCR included - text extraction must be supplied separately", "you need pre-trained weights for document domains outside those covered by released models", "you want a simple no-GPU inference solution"], "when_to_choose": ["you need state-of-the-art table detection and structure recognition from PDFs or images", "you want pre-trained weights trained on the large PubTables-1M dataset", "you need a research-grade model with training and evaluation code included"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/table-transformer", "repo": "microsoft/table-transformer", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.986876+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:32:58.447726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0c8326376c78df3efce65cdc355e8a9602eb8d1cdc96b98d1736329536b832ef", "fetched_at": "2026-08-28T04:07:30.986876+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/table-transformer"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.986876+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:32:58.447726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0c8326376c78df3efce65cdc355e8a9602eb8d1cdc96b98d1736329536b832ef", "fetched_at": "2026-08-28T04:07:30.986876+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/table-transformer"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:32:58.447726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0c8326376c78df3efce65cdc355e8a9602eb8d1cdc96b98d1736329536b832ef", "fetched_at": "2026-08-28T04:07:30.986876+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/table-transformer"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.986876+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.986876+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.986876+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:32:58.447726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0c8326376c78df3efce65cdc355e8a9602eb8d1cdc96b98d1736329536b832ef", "fetched_at": "2026-08-28T04:07:30.986876+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/table-transformer"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.986876+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.986876+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:32:58.447726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0c8326376c78df3efce65cdc355e8a9602eb8d1cdc96b98d1736329536b832ef", "fetched_at": "2026-08-28T04:07:30.986876+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/table-transformer"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.986876+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.986876+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.986876+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:32:58.447726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0c8326376c78df3efce65cdc355e8a9602eb8d1cdc96b98d1736329536b832ef", "fetched_at": "2026-08-28T04:07:30.986876+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/table-transformer"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.986876+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.986876+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:32:58.447726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0c8326376c78df3efce65cdc355e8a9602eb8d1cdc96b98d1736329536b832ef", "fetched_at": "2026-08-28T04:07:30.986876+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/table-transformer"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:32:58.447726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0c8326376c78df3efce65cdc355e8a9602eb8d1cdc96b98d1736329536b832ef", "fetched_at": "2026-08-28T04:07:30.986876+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/table-transformer"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:32:58.447726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0c8326376c78df3efce65cdc355e8a9602eb8d1cdc96b98d1736329536b832ef", "fetched_at": "2026-08-28T04:07:30.986876+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/table-transformer"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:32:58.447726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0c8326376c78df3efce65cdc355e8a9602eb8d1cdc96b98d1736329536b832ef", "fetched_at": "2026-08-28T04:07:30.986876+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/table-transformer"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "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": 1934, "days_push": 800, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}