A question about your work about mc-cnn HOT 1 OPEN

There is no data processing involved. As we wrote in the paper: a convolutional layer can be applied to inputs of arbitrary sizes. The only complication is with fully-connected layers, which have to be replaced with convolutional layers with 1x1 kernels.

To see how this is done in the code, see:

• https://github.com/jzbontar/mc-cnn/blob/master/main.lua#L661
• https://github.com/jzbontar/mc-cnn/blob/master/main.lua#L678

The network net_tr is the network used for training---it has fully-connected layers and expects 9x9 images on input; while net_te is the network used at test time, where the fully-connected layers are replaced with convolutions.

from mc-cnn.