Measured output. Named limits.
Two pose engines processed the same deterministic 288-frame sample on one CPU system. This record publishes the aggregate measurements, method, consistency result and unresolved limits without redistributing the private source video or raw result JSON.
One identity. Two engines.
The configurations reject a different input hash, frame count or sampled-frame identity. Setup and model initialisation are timed separately from the published steady-state totals.
- Input
- Private consented tennis video
- Source
- 863 frames · 29.948 FPS · 28.817 s
- Sample
- 288 frames at a 10 FPS target
- Compute
- CPU · FP32 · batch 1
- Processor
- Intel Core Ultra 7 258V · 8 cores
- Memory
- 31.51 GB available
- Software
- Python 3.11.9 · PyTorch 2.13.0+cpu
- Provenance
- Benchmark commit ccec398e5c38
The private footage and identifiable outputs are excluded. The downloadable file contains de-identified aggregate evidence only.
The model forward pass is the bottleneck.
| Keypoint R-CNN stage | Seconds | Share of total |
|---|---|---|
| Decode + sampling | 4.103228 | 0.78% |
| Inference envelope | 523.416855 | 99.16% |
| Model forward | 522.498890 | 98.99% |
| Person selection | 0.009820 | <0.01% |
| Angle analysis | 0.011832 | <0.01% |
| Serialization | 0.245471 | 0.05% |
The inference envelope includes model forward and surrounding inference work. Model-forward time is shown separately and should not be added to the envelope.
Repeatable output, not claimed accuracy.
Two retained Keypoint R-CNN CPU repetitions were compared on eight common frames. The result validates same-model output consistency under the tested conditions.
This is not ground-truth pose accuracy, biomechanics validity or coaching accuracy. Cross-model figures describe agreement between model families only.
Targets, not results.
PlannedThe audited machine has no CUDA device. GPU, reduced-precision, TensorRT and Triton performance remain unmeasured.
The open questions stay visible.
- Ground-truth pose or biomechanics accuracy.
- CUDA FP32 and reduced-precision performance.
- Behaviour under occlusion, low light and multiple-athlete scenes.
- Validated sport-specific coaching interpretation.
- Metric distance without camera calibration or a court scale.