Table 1 DNN Model parameters
From: Multi combination pattern labeling by using deep learning for chameleon rotary machine environment
DNN parameter | DNN1 | DNN2 | DNN3 |
|---|---|---|---|
Hidden layers | [128,64] | [128,64,32] | [32,16,8 ] |
Activation | Relu | ||
Output dense layers | 37 | ||
Output activation | Softmax | ||
Optimizer | Adam | ||
Loss | Categorical crossentropy | ||
Batchsize | 16 | ||
Epoch | 100 | ||