adambielski / CapsNet-pytorch

PyTorch implementation of NIPS 2017 paper Dynamic Routing Between Capsules
BSD 3-Clause "New" or "Revised" License
490 stars 73 forks source link

why use target/label to reconstruct image when test? #10

Open emobuAgent opened 4 years ago

emobuAgent commented 4 years ago

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?