Table 5 Resource metrics of transfer learning models for skin disease detection.
From: Skin disease diagnostics through federated transfer learning on heterogeneous data
Minimum | Maximum | Average | Minimum | Maximum | Average | |
|---|---|---|---|---|---|---|
Model | GPU Memory Used (%) | GPU Process Used (%) | ||||
VGG16 | 73.250 | 77.850 | 75.550 | 66.350 | 70.850 | 68.600 |
Xception | 72.950 | 77.350 | 75.150 | 65.880 | 71.250 | 68.565 |
EfficientNetB3 | 73.580 | 78.120 | 75.850 | 66.750 | 70.950 | 68.850 |
MobileNetV2 | 73.850 | 78.550 | 76.200 | 67.150 | 71.450 | 69.300 |
CPU Process Used (%) | Virtual Memory Used (%) | |||||
VGG16 | 10.250 | 11.950 | 11.100 | 79.120 | 82.580 | 80.850 |
Xception | 9.850 | 11.750 | 10.800 | 78.580 | 82.250 | 80.415 |
EfficientNetB3 | 10.650 | 11.880 | 11.265 | 79.450 | 83.150 | 81.300 |
MobileNetV2 | 10.850 | 12.050 | 11.450 | 80.250 | 83.480 | 81.865 |
