How to find wrong prediction cases in test set (CNNs using Keras)

问题

I'm using MNIST example with 60000 training image and 10000 testing image. How do I find which of the 10000 testing image that has an incorrect classification/prediction?

回答1:

Simply use model.predict_classes() and compare the output with true labes. i.e:

incorrects = np.nonzero(model.predict_class(X_test).reshape((-1,)) != y_test)

to get indices of incorrect predictions

来源：https://stackoverflow.com/questions/39300880/how-to-find-wrong-prediction-cases-in-test-set-cnns-using-keras