{"adoption": {"forks": 230, "observed_at": "2026-08-28T04:04:51.380978+00:00", "stars": 1484}, "canonical_url": "https://ross.abutalabs.com/products/deformable-convolution-v2-pytorch", "card": {"archived": false, "artifact_type": "library", "description": "Deformable ConvNets V2 (DCNv2) in PyTorch", "domain": ["deep-learning", "computer-vision", "machine-learning"], "enriched": true, "function": ["machine-learning", "deep-learning", "computer-vision", "image-processing"], "health_score": 20, "homepage": null, "language": "Cuda", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["chengdazhi/Deformable-Convolution-V2-PyTorch"], "name": "chengdazhi/Deformable-Convolution-V2-PyTorch", "platform": ["python", "cpp"], "pushed_at": "2022-11-18T21:39:26+00:00", "repo": "chengdazhi/Deformable-Convolution-V2-PyTorch", "stars": 1484, "tags": ["pytorch", "cuda", "deformable-convolution", "object-detection", "custom-operators", "mmdetection", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["add deformable convolution layers to a PyTorch model", "reproduce DCNv2 results from the paper", "improve object detection accuracy on COCO with deformable convs", "build custom CUDA operators for learnable sampling offsets", "use DCNv2 with mmdetection for detection experiments"], "what_it_is": "A PyTorch implementation of Deformable Convolution V2 (DCNv2) custom CUDA operators, ported from the original MXNet implementation. It provides the deformable conv layer used to reproduce results from the Deformable ConvNets v2 paper and has been integrated into mmdetection.", "when_to_avoid": ["you use a recent PyTorch version - the repo targets PyTorch 0.4.1 and 1.0 branches and is no longer actively updated", "you just want DCN in a modern detection framework - use the official mmdetection DCN configs instead", "you need CPU-only deformable convolution - this is a CUDA implementation"], "when_to_choose": ["you need the exact DCNv2 operator behavior described in the paper, including boundary handling fixes", "you are working with mmdetection and want the deformable conv layer it was upstreamed from", "you need efficient mini-batch deformable convolution on GPU"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/deformable-convolution-v2-pytorch", "repo": "chengdazhi/Deformable-Convolution-V2-PyTorch", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.380978+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:33:59.303726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b367d00aec7af75fe06437ebccf0a851923af453431b6875c0981784040cff8", "fetched_at": "2026-08-28T04:04:51.380978+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.380978+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:33:59.303726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b367d00aec7af75fe06437ebccf0a851923af453431b6875c0981784040cff8", "fetched_at": "2026-08-28T04:04:51.380978+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:33:59.303726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b367d00aec7af75fe06437ebccf0a851923af453431b6875c0981784040cff8", "fetched_at": "2026-08-28T04:04:51.380978+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.380978+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.380978+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.380978+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:33:59.303726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b367d00aec7af75fe06437ebccf0a851923af453431b6875c0981784040cff8", "fetched_at": "2026-08-28T04:04:51.380978+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.380978+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.380978+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:33:59.303726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b367d00aec7af75fe06437ebccf0a851923af453431b6875c0981784040cff8", "fetched_at": "2026-08-28T04:04:51.380978+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.380978+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.380978+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.380978+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:33:59.303726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b367d00aec7af75fe06437ebccf0a851923af453431b6875c0981784040cff8", "fetched_at": "2026-08-28T04:04:51.380978+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.380978+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:51.380978+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:33:59.303726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b367d00aec7af75fe06437ebccf0a851923af453431b6875c0981784040cff8", "fetched_at": "2026-08-28T04:04:51.380978+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:33:59.303726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b367d00aec7af75fe06437ebccf0a851923af453431b6875c0981784040cff8", "fetched_at": "2026-08-28T04:04:51.380978+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:33:59.303726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b367d00aec7af75fe06437ebccf0a851923af453431b6875c0981784040cff8", "fetched_at": "2026-08-28T04:04:51.380978+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:33:59.303726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b367d00aec7af75fe06437ebccf0a851923af453431b6875c0981784040cff8", "fetched_at": "2026-08-28T04:04:51.380978+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2821, "days_push": 1384, "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}}