In this section, we will look at the testing matrix for the facial emotion application. The concept of testing is really simple. We need to start observing the training steps. We are tracking the values for loss and accuracy. Based on that, we can decide the accuracy of our model. Doesn't this sound simple? We have trained the model for 30 epochs. This amount of training requires more than three hours. We have achieved 63.88% training accuracy. Refer to the code snippet in the following diagram:
Figure 10.34: Training progress for getting an idea of training accuracy
This is the training accuracy. If we want to check the accuracy on the validation dataset, then that is given in the training step as well. We have defined the validation set. With the help of this validation dataset, the trained model generates its prediction. We compare the predicted class and actual class labels. After that, we generate the validation accuracy that you can see in the preceding...