Research Article
Classification on Digital Pathological Images of Breast Cancer Based on Deep Features of Different Levels
Table 7
Hyperparameter settings for the CNN model.
| Type | Values |
| Initial learning rate | 1e − 4 | Learning rate schedule | Adam | Weight decay | 1e − 5 | Train or test batch size | 128 | Loss function | Cross-entropy loss function | Number of epochs | 100 |
|
|