Table 3 The number of parameters (in millions) and the average training time (in seconds) of an epoch for each CNN architectures
From: Plant diseases detection with low resolution data using nested skip connections
Architectures | Num. parameters | Training time | |
|---|---|---|---|
Plantvillage | Tea | ||
AlexNet | 29.78 | 2.59 | 3.86 |
VGGNet | 39.93 | 7.00 | 10.35 |
MobileNet | 3.24 | 3.51 | 5.43 |
ResNet | 23.59 | 6.85 | 10.20 |
Xception | 20.88 | 7.79 | 11.78 |
ComNet | 9.66 | 3.33 | 4.94 |