CODEWITHSUNDEEP
pythonmachine-learningtheanoconvolutionkeras
user3796320
user3796320

Reputation: 327

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

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?

Upvotes: 19

Views: 13201

Answers (2)

SnigA
SnigA

Reputation: 147

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 testing
errors = np.where(y_pred != test_generator.classes)[0] ## misclassifications done on the test data where y_pred is the predicted values
for i in errors:
    print(fnames[i])

Upvotes: 2

S.Mohsen sh
S.Mohsen sh

Reputation: 2116

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

Upvotes: 24

Related Questions