-
|
When I tried the example of ART Boundary Attack, I got the ValueError: The shape of mean and the standard deviation must be identical when the program execute classifiers.predict() |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment 1 reply
-
|
I worked it out by "classifier = KerasClassifier(clip_values=(0, 255), model=model, preprocessing=(mean_imagenet, np.ones([224, 224, 3])))" instead of classifier = KerasClassifier(clip_values=(0, 255), model=model, preprocessing=(mean_imagenet, 1)) |
Beta Was this translation helpful? Give feedback.
-
|
Hi @HuannnXu That's great! |
Beta Was this translation helpful? Give feedback.
I worked it out by "classifier = KerasClassifier(clip_values=(0, 255), model=model, preprocessing=(mean_imagenet, np.ones([224, 224, 3])))" instead of classifier = KerasClassifier(clip_values=(0, 255), model=model, preprocessing=(mean_imagenet, 1))