Table 2 Hyper-parameters of patch-based and pixel-based models
From: Deep learning for histopathological segmentation of smooth muscle in the urinary bladder
Hyper-parameters | Patch-based models | Pixel-based models |
|---|---|---|
Batch size | 32 | 4 |
Epochs | 30 | 50 |
Optimization algorithm | Stochastic Gradient Descent | Adam (beta1 = 0.9, beta2 = 0.999) |
Learning rate | 0.001 | 0.0001 |
Criterion/ Loss function | Cross-Entropy | Cross-Entropy |