PyRank
roboflow

rfdetr

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]
PyPI GitHub
More links
Download Stats
Verified repo
Monthly downloads
236.3K
Weekly downloads
66.5K
GitHub stars *
9.8K

Downloads in the 30 and 7 days to October 10, 2026. Refreshed weekly.

Package Information

Latest Version
1.11.2
Requires Python
>=3.10
Licence
Apache License 2.0
Last Release
1 week ago
First Release
March 19, 2025
Total Releases
62
Python Versions
3 3.10 3.11 3.12 3.13 3.14
No reported malware or high/critical advisories · Details

The current version has no OSV.dev malware reports and no critical or high-severity vulnerabilities.

Package Insights

What's this?
Score breakdown - each component scores 0-100, weighted by percentage
Maintenance
100
Popularity
85
Adoption
93
Community
80
Provenance
100
How the maintenance status was determined
Last commit
1 days ago
Monthly downloads
236,311
• Active
Activity within 30 days
Stable
Activity within 31-180 days
Minimal
Activity within 181-365 days, or no activity data
At Risk
No activity for > 365 days, but > 10,000 monthly downloads
Archived
Repository flagged as archived on GitHub
How the popularity category was determined
Monthly downloads
236,311
Stars
9,804
Stars per 1k downloads
41.49
Industry Standard
> 10,000,000 monthly downloads
Hidden Gem
< 0.5 stars per 1k downloads and > 100,000 monthly downloads
• Community Favorite
> 5 stars per 1k downloads
Rising Star
Balanced ratio of stars to downloads
Unknown
Fewer than 1,000 monthly downloads, or no star data
How download momentum is calculated
Week daily avg
9,497
Month daily avg
7,877
Momentum
+20.6%
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100
More insights and metrics
Python version support tiers
requires_python
>=3.10
Cutting Edge
Minimum supported version is 3.14 or newer
Modern
Minimum supported version is 3.11 to 3.13
• Legacy
Supports 3.10 or older (or Python 2)
Unknown
No requires_python specified or unparseable
License categories
License
Apache License 2.0
• Permissive
MIT, Apache, BSD, ISC, Unlicense, CC0, etc.
Copyleft
GPL, LGPL, AGPL, MPL, EPL, etc.
Proprietary
Commercial, all rights reserved, custom EULAs
Unknown
No license specified, or none of the above match
How the release cadence was determined
Last release
12 days ago
Total releases
62
Releases/year
39.4
• Rapid
Last release within 365 days and > 12 releases/year
Regular
Last release within 365 days
Slow
Last release 366-730 days ago
Stalled
Last release > 730 days ago, or no releases
Unknown
No usable release date available
How contributor risk was determined
Contributors
118
Monthly downloads
236,311
High Load
≤ 2 contributors and ≥ 50,000 monthly downloads
Moderate Load
< 10 contributors and ≥ 500,000 monthly downloads
Low Load
< 25 contributors and ≥ 5,000,000 monthly downloads, or sole maintainer with ≥ 10,000 monthly downloads
• Balanced
Enough contributors for the package's popularity
Unknown
No contributor data available
Engagement
67
 
Issue Burden
6.7
per 1k stars
Discussions
0.0
per 1k stars
Fork Ratio
9.5%
contrib / forks
Stale Release
No
 
PR Velocity
Quiet
 
Not all downloads include detailed metadata. Breakdowns reflect the subset that does.

Downloads by OS

Linux 5.5K
Windows 188
macOS 148

Python Versions

3.11
40.5% 2.4K
3.12
39.1% 2.3K
3.13
12.1% 706
3.14
4.9% 289
3.10
3.3% 195

Top Countries

1. US US
4.4K
2. IN IN
217
3. DE DE
194
4. NL NL
138
5. KR KR
101
6. SG SG
95
7. ES ES
91
8. GB GB
76
9. JP JP
74
10. CA CA
56

Weekly Downloads

GitHub Stars *

Dependencies

9
53 optional dependencies
  • albumentations<3.0.0,>=1.4.24[augment]
    extra == "augment"
  • clearml[loggers]
    extra == "loggers"
  • coreai-torch==0.4.3[coreai]
    (python_version >= "3.11" and python_version < "3.15" and ((sys_platform == "darwin" and platform_machine == "arm64") or (sys_platform == "linux" and platform_machine == "x86_64"))) and extra == "coreai"
  • coremltools<10.0,>=8.0[coreml]
    extra == "coreml"
  • executorch<1.4,>=1.3[executorch]
    python_version < "3.14" and extra == "executorch"
  • faster-coco-eval>=1.7.2[train]
    extra == "train"
  • flatbuffers>=23.5.26[tflite]
    (python_version >= "3.12" and python_version < "3.13") and extra == "tflite"
  • hotcoco==1.0.1[train]
    extra == "train"
  • jsonargparse>=4.27.7[cli]
    extra == "cli"
  • kornia<1,>=0.7[augment]
    extra == "augment"
  • litert-torch<1.0,>=0.9.4[litert]
    extra == "litert"
  • matplotlib[visual]
    extra == "visual"
  • mlflow[loggers]
    extra == "loggers"
  • onnx<2.0,>=1.16.0[onnx]
    extra == "onnx"
  • onnx<2.0,>=1.16.0[tensorrt]
    extra == "tensorrt"
  • onnx<2.0,>=1.20.0[tflite]
    (python_version >= "3.12" and python_version < "3.13") and extra == "tflite"
  • onnx-graphsurgeon[tflite]
    (python_version >= "3.12" and python_version < "3.13") and extra == "tflite"
  • onnx-graphsurgeon[onnx]
    extra == "onnx"
  • onnx2tf<3.0.0,>=2.4.0[tflite]
    (python_version >= "3.12" and python_version < "3.13") and extra == "tflite"
  • onnxconverter-common[tensorrt]
    extra == "tensorrt"
  • onnxruntime<1.24[onnx]
    python_version < "3.11" and extra == "onnx"
  • onnxruntime-gpu[tensorrt]
    extra == "tensorrt"
  • onnxsim>=0.7.0[tflite]
    (python_version >= "3.12" and python_version < "3.13") and extra == "tflite"
  • onnxsim>=0.7.0[onnx]
    extra == "onnx"
  • openvino<2027.0,>=2024.0[openvino]
    extra == "openvino"
  • pandas[visual]
    extra == "visual"
  • peft[lora]
    extra == "lora"
  • peft[train]
    extra == "train"
  • polygraphy[tflite]
    (python_version >= "3.12" and python_version < "3.13") and extra == "tflite"
  • polygraphy[tensorrt]
    extra == "tensorrt"
  • polygraphy[onnx]
    extra == "onnx"
  • protobuf>=3.20.0[loggers]
    extra == "loggers"
  • pycocotools[train]
    extra == "train"
  • pycuda>=2024.1[tensorrt-bench]
    extra == "tensorrt-bench"
  • pytorch-lightning!=2.6.2,!=2.6.3,<3,>=2.6[train]
    extra == "train"
  • rfdetr-plus<2.0.0,>=1.0.1[plus]
    extra == "plus"
  • roboflow[train]
    extra == "train"
  • scipy[train]
    extra == "train"
  • seaborn[visual]
    extra == "visual"
  • simplejpeg<2,>=1.9[train]
    extra == "train"
  • tensorboard>=2.13.0[loggers]
    extra == "loggers"
  • tensorflow>=2.16.0[tflite]
    (python_version >= "3.12" and python_version < "3.13") and extra == "tflite"
  • tensorrt>=8.6.1[tensorrt]
    extra == "tensorrt"
  • tf-keras>=2.16.0[tflite]
    (python_version >= "3.12" and python_version < "3.13") and extra == "tflite"
  • torch==2.9.*[xla]
    sys_platform == "linux" and extra == "xla"
  • torch-hungarian==0.1.0rc0[train]
    extra == "train"
  • torch-xla==2.9.*[xla]
    sys_platform == "linux" and extra == "xla"
  • torchmetrics<1.9.0,>=1.8.2[train]
    extra == "train"
  • transformer-engine<3,>=2.19[cuda]
    (sys_platform == "linux" and platform_machine == "x86_64") and extra == "cuda"
  • ultrafast-pycocotools<0.2,>=0.1.10[train]
    extra == "train"
  • vernier<0.6,>=0.5.3[train]
    extra == "train"
  • wandb[loggers]
    extra == "loggers"
  • webdataset<2,>=1.0[data]
    extra == "data"

Used By

21
View all 21 dependents

Repository details

Forks
1.2K
Issues
66
Last Commit
2 days ago
Contributors
118
Open PRs
15
Archived
No

Data and sources

Tracking Since
September 26, 2026
Data Updated
October 11, 2026
Data Freshness
Fresh
Keywords
machine-learning deep-learning vision ML DL AI DETR RF-DETR Roboflow
Sources and methodology