Research Article
Deepfake Video Detection Based on EfficientNet-V2 Network
Table 3
EfficientNetV2-S network structure.
| | Stage | Operator | Stride | Channels | Layers |
| | 1 | Conv3 ∗ 3 | 2 | 24 | 1 | | 2 | Fused-MBConv1, k3 ∗ 3 | 1 | 24 | 2 | | 3 | Fused-MBConv4, k3 ∗ 3 | 2 | 48 | 4 | | 4 | Fused-MBConv4, k3 ∗ 3 | 2 | 64 | 4 | | 5 | MBConv4, k3 ∗ 3 | 2 | 128 | 6 | | 6 | MBConv6, k3 ∗ 3 | 1 | 160 | 9 | | 7 | MBConv6, k3 ∗ 3 | 2 | 256 | 15 | | 8 | Conv1 ∗ 1&Pooling&FC | — | 1280 | 1 |
|
|
