CapsNet-pytorch icon indicating copy to clipboard operation
CapsNet-pytorch copied to clipboard

why use target/label to reconstruct image when test?

Open emobuAgent opened this issue 5 years ago • 0 comments

In inference time , why use the label to reconstruct the image while not use the prediction of the model and the digit capsules as the input of reconstruction module? If the predict is wrong, the reconstruction module will reconstruct the wrong class of image?

emobuAgent avatar Jun 10 '20 09:06 emobuAgent