Table 1.
The hyper-parameters in the ResNet.
| Symbol | Description | Value |
|---|---|---|
| K | Kernel matrix | |
| p | Number of kernels in convolutional layers | 32 |
| b | Mini-batch size | 10 |
| Initial value of learning rate | 0.001 | |
| The decay rate of learning rate | 0.0002 | |
| Initial value of the first-order moment | 0 | |
| Initial value of the second-order moment | 0 | |
| The exponential decay rate of the first-order moment estimation | 0.9 | |
| The exponential decay rate of the second-order moment estimation | 0.999 | |
| A minimum value close to zero |