Deep Learning With Keras 简明教程

Predicting on Test Data

预测未知数据中的数字很容易。您只需调用 model 的 predict_classes 方法，方法是将其传递给包含未知数据点的向量。

To predict the digits in an unseen data is very easy. You simply need to call the predict_classes method of the model by passing it to a vector consisting of your unknown data points.

predictions = model.predict_classes(X_test)

该方法调用在一个向量中返回预测，这个向量可以针对实际值进行 0 和 1 的测试。这是通过以下两个语句完成的：

The method call returns the predictions in a vector that can be tested for 0’s and 1’s against the actual values. This is done using the following two statements −

correct_predictions = np.nonzero(predictions == y_test)[0]
incorrect_predictions = np.nonzero(predictions != y_test)[0]

最后，我们将使用以下两个程序语句打印预测正确和不正确的计数：

Finally, we will print the count of correct and incorrect predictions using the following two program statements −

print(len(correct_predictions)," classified correctly")
print(len(incorrect_predictions)," classified incorrectly")

运行代码时，您将获得以下输出：

When you run the code, you will get the following output −

9837 classified correctly
163 classified incorrectly

现在，您已经对模型进行了满意的训练，我们将保存它以备将来使用。

Now, as you have satisfactorily trained the model, we will save it for future use.