{"adoption": {"forks": 176, "observed_at": "2026-08-28T04:03:59.539312+00:00", "stars": 1207}, "canonical_url": "https://ross.abutalabs.com/products/ranger-deep-learning-optimizer", "card": {"archived": false, "artifact_type": "library", "description": "Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase", "domain": ["deep-learning", "machine-learning"], "enriched": true, "function": ["machine-learning", "deep-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["lessw2020/Ranger-Deep-Learning-Optimizer"], "name": "lessw2020/Ranger-Deep-Learning-Optimizer", "platform": ["python"], "pushed_at": "2023-12-22T13:24:12+00:00", "repo": "lessw2020/Ranger-Deep-Learning-Optimizer", "stars": 1207, "tags": ["optimizer", "radam", "lookahead", "gradient-centralization", "pytorch"], "topics": [], "urls": [], "use_cases": ["optimize neural network training in pytorch", "improve image classifier accuracy over adamw", "train deep learning models with radam and lookahead", "apply gradient centralization to conv and fc layers", "beat fastai leaderboard scores with a better optimizer"], "what_it_is": "Ranger is a PyTorch deep learning optimizer that synergistically combines RAdam (Rectified Adam), LookAhead, and Gradient Centralization in a single codebase. It is a drop-in optimizer intended to improve training stability and final accuracy compared to standard Adam/AdamW.", "when_to_avoid": ["you need actively developed optimizers - consider Ranger21 or torch.optim built-ins", "you are not using PyTorch", "you need guaranteed state-of-the-art results on your specific task without benchmarking"], "when_to_choose": ["you are training PyTorch models and want a stronger optimizer than AdamW", "you want to experiment with RAdam, LookAhead, and Gradient Centralization together", "you are following fastai-style training recipes with flat LR plus cosine annealing"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/ranger-deep-learning-optimizer", "repo": "lessw2020/Ranger-Deep-Learning-Optimizer", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.539312+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:18:59.314694+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1c7b76f55b705ccd2d0cb4e334ff876456267b2c4801b2361e417b4341ebde9", "fetched_at": "2026-08-28T04:03:59.539312+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lessw2020/Ranger-Deep-Learning-Optimizer"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.539312+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:18:59.314694+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1c7b76f55b705ccd2d0cb4e334ff876456267b2c4801b2361e417b4341ebde9", "fetched_at": "2026-08-28T04:03:59.539312+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lessw2020/Ranger-Deep-Learning-Optimizer"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:18:59.314694+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1c7b76f55b705ccd2d0cb4e334ff876456267b2c4801b2361e417b4341ebde9", "fetched_at": "2026-08-28T04:03:59.539312+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lessw2020/Ranger-Deep-Learning-Optimizer"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.539312+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.539312+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.539312+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:18:59.314694+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1c7b76f55b705ccd2d0cb4e334ff876456267b2c4801b2361e417b4341ebde9", "fetched_at": "2026-08-28T04:03:59.539312+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lessw2020/Ranger-Deep-Learning-Optimizer"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.539312+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.539312+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:18:59.314694+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1c7b76f55b705ccd2d0cb4e334ff876456267b2c4801b2361e417b4341ebde9", "fetched_at": "2026-08-28T04:03:59.539312+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lessw2020/Ranger-Deep-Learning-Optimizer"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.539312+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.539312+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.539312+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:18:59.314694+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1c7b76f55b705ccd2d0cb4e334ff876456267b2c4801b2361e417b4341ebde9", "fetched_at": "2026-08-28T04:03:59.539312+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lessw2020/Ranger-Deep-Learning-Optimizer"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.539312+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.539312+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:18:59.314694+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1c7b76f55b705ccd2d0cb4e334ff876456267b2c4801b2361e417b4341ebde9", "fetched_at": "2026-08-28T04:03:59.539312+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lessw2020/Ranger-Deep-Learning-Optimizer"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:18:59.314694+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1c7b76f55b705ccd2d0cb4e334ff876456267b2c4801b2361e417b4341ebde9", "fetched_at": "2026-08-28T04:03:59.539312+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lessw2020/Ranger-Deep-Learning-Optimizer"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:18:59.314694+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1c7b76f55b705ccd2d0cb4e334ff876456267b2c4801b2361e417b4341ebde9", "fetched_at": "2026-08-28T04:03:59.539312+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lessw2020/Ranger-Deep-Learning-Optimizer"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:18:59.314694+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1c7b76f55b705ccd2d0cb4e334ff876456267b2c4801b2361e417b4341ebde9", "fetched_at": "2026-08-28T04:03:59.539312+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lessw2020/Ranger-Deep-Learning-Optimizer"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2571, "days_push": 985, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}