diff --git "a/index.html" "b/index.html" --- "a/index.html" +++ "b/index.html" @@ -496,7 +496,7 @@ Each point is a public validation session: color = platform, shape = model family (● 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. + inference time and not the accelerator's core-throughput ceiling. ⚠ flagged sessions are shown at their measured accuracy.
@@ -516,13 +516,13 @@Each point is one model × platform validation session: color = platform, shape = model family - (● YOLOv5 · ■ YOLOv8 · ▲ YOLO11 · ◆ YOLO26). X is the theoretical FPS — the accelerator's + (● YOLOv5 · ■ YOLOv8 · ▲ YOLO11 · ◆ YOLO26). X is the core-throughput ceiling (FPS) — the accelerator's compute ceiling (1000 ÷ isolated device-compute time); Y is the realized FPS actually delivered by the full validation pipeline. The dashed diagonal is parity (realized = ceiling): the closer a point sits to it, the less the host pipeline — JPEG decode and the validation-only 0.001 confidence threshold — costs on that @@ -620,14 +620,14 @@
Realized FPS is the measured steady-state throughput — stages overlap across frames, so it exceeds - 1000 ÷ end-to-end latency. Theoretical FPS (~) is the + 1000 ÷ end-to-end latency. Core-throughput ceiling (FPS) (~) is the accelerator's per-stage compute ceiling, approachable in production when the accelerator — not host JPEG decode or the validation-only 0.001 confidence threshold — is the bottleneck; see the ceiling chart on the Performance tab. Measured by the @@ -645,7 +645,7 @@