Table 8 Performance evaluation of autoenocder, QAE-f16 and QAE-u8 models on Raspberry Pi IoT device
Methods | Memory size (bytes) | Average memory utilization (MiB) | Peak memory utilization(MiB) | Average CPU utilization | Peak CPU utilization | Time consumption (s) |
|---|---|---|---|---|---|---|
Autoencoder | 79,432 | 154.23 | 219.19 | 115.87 | 184 | 34 |
QAE-f16 | 8368 | 51.64 | 63.84 | 107.31 | 201 | 24 |
QAE-u8 | 6168 | 46.24 | 57.06 | 111.51 | 147 | 15 |