Each point is a public validation session: color = platform, shape = model family - (● YOLOv5 · ■ YOLOv8 · ▲ YOLO11 · ◆ YOLO26). X axis is sustained pipelined throughput on a log - scale — the full image load → decode → preprocess → inference → postprocess pipeline, not bare - inference time. ⚠ flagged sessions are shown at their measured accuracy. + (● YOLOv5 · ■ YOLOv8 · ▲ YOLO11 · ◆ YOLO26). X axis is the realized sustained throughput on a log + scale — the measured full image load → decode → preprocess → inference → postprocess pipeline, not bare + inference time and not the accelerator's theoretical ceiling. ⚠ flagged sessions are shown at their measured accuracy.
- Throughput is the measured pipelined rate — stages overlap across frames, so it exceeds - 1000 ÷ end-to-end latency. Measured by the + Realized FPS is the measured steady-state throughput — stages overlap across frames, so it exceeds + 1000 ÷ end-to-end latency. The full per-session table also reports a Theoretical FPS: the + accelerator's per-stage ceiling, approachable in production when the accelerator — not host JPEG decode or the + validation-only 0.001 confidence threshold — is the bottleneck. Measured by the EdgeFirst Profiler.
@@ -622,7 +625,7 @@