Table 2 Experimental results of improved-YOLOX networks
From: A lightweight YOLOX-based model for detection of metallic gaskets on High-speed EMU wheelset
Model | mAP | Latency (ms) | FLOPs (GB) | Param (MB) |
|---|---|---|---|---|
YOLOX-S | 38.81 | 386.14 | 26.80 | 9.0 |
YOLOX-Nano | 35.70 | 23.35 | 1.08 | 0.91 |
YOLOX-LH | 39.16 | 383.65 | 26.71 | 9.0 |
YOLOX-Shuf2 | 36.28 | 36.28 | 19.06 | 1.28 |
YOLOXLite | 38.40 | 1.03 | 1.03 | 0.916 |