Python Deep Learning Projects

Evaluating the model

Now, let’s evaluate the model and capture the loss and the accuracy:

# 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 8.26: Printout of the evaluation of the convolution classifier with max pooling and dropout

We can see that the model is 98.42% accurate on the test data, 98.52% on the validation data, and 99.26% on the train data. The convolution model with pooling and dropout gives the same level of performance as the convolution model without pooling, but with four times fewer parameters. If you look at ...