Table 1 Hyper parameters of all used neural networks
From: Gear Pitting Measurement by Multi-Scale Splicing Attention U-Net
Hyper parameter | Value |
|---|---|
Learning rate | 0.0025 |
Optimization algorithm | SGD |
Multiple of learning rate change | 0.1 |
Step of learning rate change | 20000 |
Rotation_range | 0.2 |
Height_shift_range | 0.05 |
Width_shift_range | 0.05 |
Zoom_range | 0.05 |
Shear_range | 0.05 |
Steps_per_epoch | 1000 |
Epochs | 400 |
Batch size | 2 |