diff --git "a/index.html" "b/index.html" --- "a/index.html" +++ "b/index.html" @@ -504,13 +504,15 @@

Accuracy vs On-target Latency

End-to-end per-image latency measured by the EdgeFirst Profiler on deployment hardware
-
-

- On-target latency results are being collected across the platform matrix. - See the EdgeFirst Profiler documentation - for how profiling and validation are performed. -

-
+
+

+ Each point is a public validation session: color = platform, shape = model family + (● YOLOv5 · ■ YOLOv8 · ▲ YOLO11 · ◆ YOLO26). X axis is end-to-end per-image latency + (load → decode → preprocess → inference → postprocess) on a log scale — lower is better, so + the top-left is the sweet spot. For the i.MX 95 Neutron runner the latency-optimized pipeline + (--serialize-core) is shown here; its throughput-optimized counterpart is on the + chart above. +

@@ -646,8 +648,8 @@ - - + +