Research Article
[Retracted] Emotion Recognition of Students Based on Facial Expressions in Online Education Based on the Perspective of Computer Simulation
Table 1
The parameters of the applied CNN model.
| Layers | Kernel number | Kernel size | Steps | Image size |
| Input | 0 | 0 | None | 48 × 48 × 1 | Convolutional 0 | 32 | 1 × 1 | 1 | 48 × 48 × 32 | Convolutional 1-1 | 64 | 3 × 3 | 1 | 48 × 48 × 64 | Convolutional 1-2 | 64 | 5 × 5 | 1 | 48 × 48 × 64 | Pooling 1 | 0 | 2 × 2 | 2 | 24 × 24 × 64 | Convolutional 2-1 | 64 | 3 × 3 | 1 | 24 × 24 × 64 | Convolutional 2-2 | 64 | 5 × 5 | 1 | 24 × 24 × 64 | Pooling 2 | 0 | 2 × 2 | 2 | 12 × 12 × 64 | Fully connected 1 | | Dropout = 0.5 | | 1 × 1 × 2048 | Fully connected 2 | | Dropout = 0.5 | | 1 × 1 × 1024 | Output | 0 | 0 | None | 1 × 1 × 8 |
|
|