Table 1 Pre-trained deep learning models using ImageNet.
From: Analysis of facial ultrasonography images based on deep learning
Model | Depth | Size (MB) | Parameters (millions) | Image input size |
|---|---|---|---|---|
AlexNet | 8 | 227 | 61 | 227 × 227 |
DenseNet-201 | 201 | 77 | 20 | 224 × 224 |
GoogleNet | 22 | 27 | 7 | 224 × 224 |
Inception-ResNet-v2 | 164 | 209 | 55.9 | 299 × 299 |
Inception-v3 | 48 | 89 | 23.9 | 299 × 299 |
Mobilenet-v2 | 53 | 13 | 3.5 | 224 × 224 |
NasNet-Mobile | a | 20 | 5.3 | 224 × 224 |
ResNet-18 | 18 | 44 | 11.7 | 224 × 224 |
ResNet-50 | 50 | 96 | 25.6 | 224 × 224 |
ResNet-101 | 101 | 167 | 44.6 | 224 × 224 |
ShuffleNet | 50 | 5.4 | 1.4 | 224 × 224 |
SqueezeNet | 18 | 5.2 | 1.24 | 227 × 227 |
VGG-16 | 16 | 515 | 138 | 224 × 224 |
VGG-19 | 19 | 535 | 144 | 224 × 224 |
Xception | 71 | 85 | 22.9 | 299 × 299 |
