Table 2.
Hyperparameters | Value |
---|---|
Optimization | SGD |
Initial learn rate | 0.01629 |
Momentum | 0.98 |
Weight decay | 4.5 × 10−4 |
Batch size | 16 |
Epoch | 100 |
Hyperparameters | Value |
---|---|
Optimization | SGD |
Initial learn rate | 0.01629 |
Momentum | 0.98 |
Weight decay | 4.5 × 10−4 |
Batch size | 16 |
Epoch | 100 |