rk-bench 公佈 RK3588 INT8 實測：YOLOv8n 提速 1.96×、YOLO11n 提速 1.40×，新增 OCR 測試
RK3588 INT8, measured: 1.96 on YOLOv8n, 1.4 on YOLO11n — plus OCR joins the bench
Anguo 更新 rk-bench v0.2.0 的 RK3588 排行榜，公佈 YOLOv8n、YOLOv5s（ReLU）和 YOLO11n 的 INT8 對 FP 實測，提速分別為 1.96×、1.84× 和 1.40×。
Posted on Nov 2 Edited on Nov 2
Follow-up to the first rk-bench leaderboard: same RK3588, same frozen protocol (PERF_RUN hardware timing, per-layer CPU-fallback verdicts, median of 3 independent sessions). v0.2.0 adds the two things readers asked for.
INT8 vs FP, same models, same board
Quantized with Toolkit2 2.3.2 using the RKNN Model Zoo's own recipe and its own 20-image COCO calibration subset (each entry's notes say so):
| Model | FP p50 | INT8 p50 | Speedup | Verdict |
|---|---|---|---|---|
| YOLOv8n | 37.50 ms | 19.17 ms | 1.96× | NPU_ONLY → NPU_ONLY |
| YOLOv5s (ReLU) | 37.80 ms | 20.52 ms | 1.84× | NPU_ONLY → NPU_ONLY |
| YOLO11n | 43.67 ms | 31.20 ms | 1.40× | NPU_ONLY → NPU_ONLY |
So on RK3588, INT8 buys you roughly 2× on the older YOLO generations and 1.4× on YOLO11n — and in all three cases the quantized graph stays entirely on the NPU. Model files roughly halve (7.25 → 4.13 MB for YOLOv8n).
OCR rows, and a second CPU stowaway
-
PP-OCRv4-Det (480×480): 47.86 ms,
NPU_ONLY -
PP-OCRv4-Rec (48×320): 22.68 ms,
MIXED— one Reshape immediately after the softmax executes on the CPU: 579 µs, 2.58% of frame time.
That makes two MIXED models on the board (RetinaFace was the first), and both were caught by the per-layer verdict — neither is visible from end-to-end timing. This is exactly the failure mode a leaderboard should surface.
The bug in my own tool
Adding INT8 rows exposed a real bug in rk-bench itself: a leaderboard row's identity was model+variant, so the first INT8 report replaced its FP twin instead of sitting next to it. Identity now includes precision, there's a regression test, and the published leaderboard was rebuilt from the raw reports and verified row by row (15 rows). If you cloned v0.1.0's data, re-pull.
Also new in the tool: rkbench run --note records provenance (calibration sets, conversion quirks) in the report, so a number's paperwork travels with it.
Full table: docs/LEADERBOARD.md · Release: v0.2.0
Next open items: the RK3576 board table (seeded as a good first issue — if you have the board, the anchor models take ~10 minutes), and --core-mask measurements. Requests welcome in the bench-report issues.
來源：DEV Community · dev.to