Table 2 Comparison of the number of parameters and computational complexity of SMART with DeepSC and SSS.
From: The self supervised multimodal semantic transmission mechanism for complex network environments
Model name | Number of participants (M) | Theoretical FLOPs (G) | RTX 3090 inference latency (ms) | Jetson AGX Xavier inference latency (ms) |
|---|---|---|---|---|
SMART | 25.8 | 29.0 | 17.2 | 47.3 |
DeepSC | 23.4 | 25.0 | 20.5 | 55.0 |
SSS | 18.2 | 20.0 | 22.3 | 60.0 |
