Python Deep Learning Projects

Evaluating the model

You can evaluate the convolution model on the test data 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 8.12: Printout of the evaluation of the convolution classifier

We can see that the model is 97.92% accurate on test data, 97.72% on validation data, and 99.71% on train data. It is clear from the loss as well that the model is slightly overfitting on the train data. We will talk about how to handle overfitting later.

Now, let's plot the train and validation metrics to see how the ...