Python Deep Learning Projects

Evaluating the model

Now, evaluate the model with the following code:

# evaluate modelloss,acc = model.evaluate(X_test, y_test)print('Test loss:', loss)print('Accuracy:', acc)

The following is the output of the preceding code:

Figure 8.30: Printout of the evaluation of the deep convolution classifier

We can see that the model is 99.01% accurate on the test data, 98.84% on the validation data, and 98.38% on the train data. The deeper convolution model with pooling and dropout gives a much better performance with just 110,000 parameters. If you look at the loss as well, this model was able to reach a better minima than the other models that ...