Table 8 Network architecture of the age/gender classification CNN [26]
From: Effective hyperparameter optimization using Nelder-Mead method in deep learning
Conv 1 | Kernel size: 7, stride: 4, pad: 0 |
Pool 1 (MAX pooling) | Kernel size: 3, stride: 2, pad: 0 |
Conv 2 | Kernel size: 5, stride: 1, pad: 2 |
Pool 2 (MAX pooling) | Kernel size: 3, stride: 2, pad: 0 |
Conv 3 | Kernel size: 3, stride: 1, pad: 1 |
Pool 3 (MAX pooling) | Kernel size: 3, stride: 2, pad: 0 |
FC 1 | Dropout |
FC 2 | Dropout |
FC 3 | Â |