Convolutions and max-pooling are performed in the encoder, where 13 convolutional layers are taken from VGG-16. The corresponding max-pooling indices are stored while performing 2×2 max-pooling.





















































Convolutions and max-pooling are performed in the encoder, where 13 convolutional layers are taken from VGG-16. The corresponding max-pooling indices are stored while performing 2×2 max-pooling.