How to find wrong prediction cases in test set (CNNs using Keras)
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
Editing as was not clear earlier
To identify the image files that are wrongly classified, you can use:
fnames = test_generator.filenames ## fnames is all the filenames/samples used in testingerrors = np.where(y_pred != test_generator.classes)[0] ## misclassifications done on the test data where y_pred is the predicted valuesfor i in errors: print(fnames[i])