Reconstructing a classified image from a simple Convolution Neural Network

Question

I have a CNN trained on a classification task (Network is simple, 2 convolution + pooling layers and 2x fully connected layers). I would like to use this to reconstruct an image if I input a classification label.

Is this possible to achieve?

Is it possible to share weights between corresponding layers in the 2 networks?

Answer 1

您应该看一下cGAN的实现，以及为什么不从Google获得DeepDream;）答案是yes it is possible ，但并非一帆风顺