Research Article
Railway Fastener Fault Diagnosis Based on Generative Adversarial Network and Residual Network Model
Table 2
Generator network algorithm.
| | Generating network algorithm |
| | Input: Gaussian noise N | | Output: Composite data G(Z) | | 1 Initialization of relevant parameters | | Set up the training cycle (e): epoch | | Set up the batch sample size (m): batch size | | 2 Begin | | 3 For i = 1 in e do | | 4 For batch = 1 in m do | | 5 | | 6 Optimize loss functions | | 7 Update weight and bias | | 8 End | | 9 End | | 10 End |
|
|