Research Article
Classification on Digital Pathological Images of Breast Cancer Based on Deep Features of Different Levels
Table 12
Hyperparameter settings for the MFNN model.
| Type | Value |
| Initial learning rate | 1e − 3 | Learning rate schedule | SGD | Weight decay | 1e − 5 | Train or test batch size | 512 | Loss function | Cross-entropy loss function | Number of epochs | 500 |
|
|