Skip to main content
. 2019 Dec 27;20(1):172. doi: 10.3390/s20010172

Figure 7.

Figure 7

Graphs showing the effect of hyperparameters on the training progress. (a) History of the model with 100 epochs, a batch size of 32, and a default learning rate of 0.001; (b) History of model with 1000 epochs, a batch size of 32, and a default learning rate of 0.001; (c) History of model with 1000 epochs, a batch size of 128, and a learning rate of 0.0001; (d) History of model with 1000 epochs, a batch size of 128, a learning rate of 0.0001, and an L2 weight decay value of 0.001.