Models · Pose estimation

RF-DETR Keypoint

Roboflow RF-DETR Keypoint Preview: predicts people and their 17 COCO joints from a whole image using a DINOv2 backbone and transformer decoder. Apache-2.0 code and preview weights.

stable Fork of roboflow/rf-detr@5b22dfc · backends: portable, kernels

Checkpoint rf-detr-keypoint-preview

Paper 2025 Added in 0.2.0 Evaluated with 0.2.0

Kernels, RTX 5060 Ti 16 GB 9.46 ms 1080x1920, fp16
vs the faster original 2.0× original fp16: 19.3 ms
Peak memory 176 MiB original: 186 MiB
Accuracy vs original fp32 ±0.0 kernels keypoint AP, COCO val2017 (71.8 original)

Use it

pip install fastforks

Lean install with only what this model needs: pip install "fastforks-core[torchvision,transformers]"

from fastforks import pose

model = pose.load("rf-detr-keypoint-preview")  # kernels on a supported GPU, else portable PyTorch
result = model(image, boxes=...)
result.keypoints  # also: keypoint_scores, boxes, scores
result.backend  # what ran: mode, device, dtype, kernels
fastforks bench rf-detr-keypoint-preview

Times the model on this machine. load(…, mode="portable") or mode="kernels" picks a backend; usage guide.

Speed and memory

Every backend on one GPU (RTX 5060 Ti 16 GB) and the same input, the authors’ code included. Kernels runs fp16. Portable runs fp16 on CUDA.

Input: synthetic, 1080x1920 (the task’s standard size)

BackenddtypeTime per call (ms)vs original fp16Peak memory
allocated / reserved
Load (s)First call (s)
Original fp32pinned RF-DETR torchvision resize/normalize, original network and uncertainty-fused PostProcessfp32 29.40.65×305 MiB/322 MiB4.70.66
Original fp16the authors' float16 model option; pinned RF-DETR torchvision resize/normalize, original network and uncertainty-fused PostProcess; authors inference(compile=False, dtype=float16, inplace=True)fp16 19.3–186 MiB/244 MiB1.50.08
Portable fp32fp32not measured ––––
Portablefp16 18.21.1×179 MiB/204 MiB2.70.38
Kernelsfp16 9.462.0×176 MiB/224 MiB3.80.45
Portable + torch.compile 8.002.4×191 MiB/220 MiB48 (build)–
TensorRT fp16network on person crops onlyfp16 4.284.5×124 MiBenginenot comparable67 (build)–

Measured on RTX 5060 Ti 16 GB, torch 2.14.1+cu130, 2026-11-11 to 2026-11-16. First call, 3 warm-up, peak reset, median of 3 rounds x median of 5. Ratios divide two times of this table (same GPU, same input). Original fp16 is the authors’ own precision option, else torch.autocast. torch.compile and TensorRT: build time instead of load time. TensorRT memory (engine, not comparable) is the GPU memory the engine took, read from the driver because TensorRT allocates outside PyTorch, so it can't be compared with the PyTorch peaks of the other rows.

Other devices

DeviceBackenddtypems / callPeak memoryOutput vs referenceInput
Apple M1 Pro 16 GB MPS, torch 2.14.1, 2026-11-12Originalfp32148 2,074 MiB process–1080x1920
Portablefp16135 1,737 MiB processdiffers1080x1920
Portablefp32148 1,830 MiB processmatches1080x1920
Kernelsfp16not implemented–1080x1920

CUDA memory is torch’s peak allocated / reserved; Apple has no such counter, so the Mac rows show the process footprint (weights, Python and torch included). “Output vs reference” compares the device’s output with the stored golden output under the card’s tolerance; – = not checked on that device. Kernels “not implemented” = no kernels for this model on that backend yet: it runs portable there.

Licence and weights

Commercial use allowed

Code
Apache-2.0 LICENSE
Weights
Apache-2.0 source
Training data

Our reading of the licences, not legal advice.

Weights

rf-detr-keypoint-preview-xlarge.pth 164 MB· hosted on repo.roboflow.com

fastforks downloads and checks these files on first use (fastforks download rf-detr-keypoint-preview).

Accuracy

The test set through the authors’ code and through ours: same checkpoint, same protocol. The distance between the original’s fp32 and fp16 runs is what half precision alone costs; our runs should stay within it.

COCO val2017

predicted people, keypoint AP

Rundtypekeypoint AP ↑Δ keypoint AP vs fp32 originalimagesms / image
Original fp32fp3271.8 reference 5000 –
Original fp16fp1671.8 +0.0 5000 –
Portable fp32not measured
Portablefp1671.8 +0.0 5000 –
Kernelsfp1671.8 ±0.0 5000 –

Bottom-up on all 5,000 validation images, no ground-truth boxes; people ranked by their predicted person score, after model-specific decoding; pycocotools OKS AP. Original = the authors’ code, same checkpoint and protocol. Measured on original fp32, original fp16: RTX 5060 Ti, torch 2.14.1+cu130, 2026-11-11; portable, kernels: RTX 5060 Ti, torch 2.14.1+cu130, fastforks 0050000f, 2026-11-11.

COCO val2017

every 10th image, predicted people, keypoint AP

Rundtypekeypoint AP ↑Δ keypoint AP vs fp32 originalimagesms / image
Original fp32fp3272.7 reference 500 –
Original fp16fp1672.9 +0.2 500 –
Portable fp32fp3272.7 +0.0 500 32.4
Portablefp1672.9 +0.2 500 –
Kernelsfp1672.8 +0.1 500 –

Bottom-up on the same every-tenth-image subset for all modes, ranked by predicted person score after model-specific decoding; pycocotools OKS AP. Original = the authors’ code, same checkpoint and protocol. Measured on original fp32, original fp16: RTX 5060 Ti, torch 2.14.1+cu130, 2026-11-11; portable fp32: RTX 5060 Ti, torch 2.14.1+cu130, fastforks 44640884, 2026-11-17; portable, kernels: RTX 5060 Ti, torch 2.14.1+cu130, fastforks 0050000f, 2026-11-11.

Closeness to the original

Beyond the test-set scores: the raw output of ours against the original’s fp32 output on the same input, pixel by pixel. CPU, float32: max |diff| <= 0.0001 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.12 and p99 <= 0.32 (absolute error of the output keypoints).

CheckToleranceMeasured
CPU fp32, max |diff|≤ 0.0001 not recorded
GPU default dtypes, mean |diff|≤ 0.12 0.07925
GPU default dtypes, p99 |diff|≤ 0.32 0.21301
gpu_min_score≤ 0.3 not recorded

Recorded for rf-detr-keypoint-preview on RTX 5060 Ti, torch 2.14.1+cu130, 2026-11-11, with these kernels: fastbb

Details

Roboflow RF-DETR Keypoint Preview: a DINOv2-small backbone with windowed attention and a deformable transformer decoder that predicts people and 17 COCO joints directly from the whole image. The 40.7M-parameter Apache-2.0 preview uses 576 x 576 square inputs and conditional keypoint queries. Person confidence includes the upstream localization-uncertainty fusion; joint confidence is findability. No person detector, boxes or NMS are required.

Input / output
Input: one RGB image and a box per person. Output: keypoints with confidence scores for every person.
Input size
any H x W >= 32, padded to a multiple of 32; tested up to 3000x4000 (526 MiB allocated)
Options
  • score_threshold=0.50.0 to 1.0· changes the output
Outputs
keypoints, keypoint_scores, boxes, scores
CUDA kernels
  • fastbbfast backbone kernels: flash attention, window attention, instance norm and rotary embeddings for ViT and similar backbones
Apple (MPS)
fp32, fp16

Limitations

  • Requires the optional transformers and torchvision libraries.
  • This is the Apache-2.0 Keypoint Preview checkpoint; restricted RF-DETR Plus detection variants are not included.
  • module() exports raw boxes, class logits and keypoint predictions; confidence fusion and thresholding remain outside the exported graph.
  • Float16 and float32 may retain different people near the score threshold; raw query ordering can differ across export engines.
  • torch.compile uses upstream positional-interpolation graph breaks; fullgraph=True is unsupported. Fixed-shape torch.export and ONNX remain supported.
Full reference, generated from the repository

Roboflow RF-DETR Keypoint Preview: predicts people and their 17 COCO joints from a whole image using a DINOv2 backbone and transformer decoder. Apache-2.0 code and preview weights.

Commercial use: yes.

variantinputbackendtime (ms)peak memory (MiB, allocated / reserved)
rf-detr-keypoint-previewsynthetic (1080x1920)original (fp32)
original
portable
kernels
portable + torch.compile
TensorRT fp16
29.4
19.3
18.2
9.46
8.00
4.28 (network on person crops only)
305 / 322
186 / 244
179 / 204
176 / 224
191 / 220
264 / 294
Details
  • Original code: https://github.com/roboflow/rf-detr at 5b22dfc09406
  • Code licence: Apache-2.0 (permissive); files: LICENSE
  • Weights licence: Apache-2.0
  • Licence evidence: https://github.com/roboflow/rf-detr/blob/5b22dfc0940697ce1abdfa681a5f7392b3eddbfb/README.md#keypoints
  • Training data: COCO 2017 (train, instance annotations), LVD-142M (DINOv2's curated web-image set, not released) (Author README: pretrained on COCO person keypoints; DINOv2-small backbone originates from LVD-142M pretraining. Full intermediate training provenance is not stated.)
  • Options: score_threshold = 0.5 (0.0 to 1.0)
  • Kernel libraries: fastbb
  • Variants: rf-detr-keypoint-preview
  • Outputs: keypoints, keypoint_scores, boxes, scores; label_set: coco-keypoints-17
  • Input size: any H x W >= 32, padded to a multiple of 32
  • Tested up to (portable, fp16, RTX 5060 Ti 16 GB): rf-detr-keypoint-preview 3000x4000 (0.5 GiB peak allocated, 0.6 reserved)
  • rf-detr-keypoint-preview 1080x1920, first call: portable + torch.compile 48 s (cold Inductor cache), TensorRT fp16 67 s (ONNX + engine).
  • rf-detr-keypoint-preview original (fp32) 1080x1920: pinned RF-DETR torchvision resize/normalize, original network and uncertainty-fused PostProcess
  • rf-detr-keypoint-preview original 1080x1920: the authors' float16 model option; pinned RF-DETR torchvision resize/normalize, original network and uncertainty-fused PostProcess; authors inference(compile=False, dtype=float16, inplace=True)
  • rf-detr-keypoint-preview load / first call: original 1.49 s / 0.083 s, portable 2.66 s / 0.386 s, kernels 2.7 s / 0.384 s
  • Protocol, first call, 3 warm-up, peak reset, median of 3 rounds x median of 5

Measured

Bottom-up on all 5,000 validation images, no ground-truth boxes; people ranked by their predicted person score, after model-specific decoding; pycocotools OKS AP. Bottom-up on the same every-tenth-image subset for all modes, ranked by predicted person score after model-specific decoding; pycocotools OKS AP. Original = the original code named under Details, same checkpoint and protocol.

variantdatasetoriginal fp32original fp16portableportable fp32kernelsnote
rf-detr-keypoint-previewCOCO val2017, predicted people, keypoint AP71.871.871.871.8
rf-detr-keypoint-previewCOCO val2017, every 10th image, predicted people, keypoint AP72.772.972.972.772.8

Measured on portable: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 0050000f, 2026-11-11; portable32: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 44640884, 2026-11-17; kernels: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 0050000f, 2026-11-11.

Parity

CPU, float32: max |diff| <= 0.0001 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.12 and p99 <= 0.32 (absolute error of the output keypoints).

variantkernels error vs original, mean / p99GPU, torchkernels used
rf-detr-keypoint-preview0.07925 / 0.21301RTX 5060 Ti, torch 2.14.1+cu130fastbb@7d058322634d:sm_120

Limitations

  • Requires the optional transformers and torchvision libraries.
  • This is the Apache-2.0 Keypoint Preview checkpoint; restricted RF-DETR Plus detection variants are not included.
  • module() exports raw boxes, class logits and keypoint predictions; confidence fusion and thresholding remain outside the exported graph.
  • Float16 and float32 may retain different people near the score threshold; raw query ordering can differ across export engines.
  • torch.compile uses upstream positional-interpolation graph breaks; fullgraph=True is unsupported. Fixed-shape torch.export and ONNX remain supported.

Example output

One fixed input through this checkpoint, the same for every model of the task (kernels · float16 · NVIDIA GeForce RTX 5060 Ti).

Input
Output
Astronaut Eileen Collins, input
Input · 100%

Input: Astronaut Eileen Collins, NASA (public domain).