Implementing DeepDream
Another use for trained CNNs is exploiting the fact that some intermediate nodes detect features of labels (for instance, a cat's ear, or a bird's feather). Using this fact, we can find ways to transform any image to reflect those node features for any node we choose. For this recipe, we will go through the DeepDream tutorial on TensorFlow's website, but we will cover the essential parts in much more detail. The hope is that we can prepare the reader to use the DeepDream algorithm to explore CNNs, and features created in them.
Getting ready
TensorFlow's official tutorials show how to implement DeepDream through a script (refer to the first bullet point in the next See also section). The purpose of this recipe is to go through the script they provide and explain each line. While the tutorial is great, there are some parts that are skippable and some parts that could use more explanation. We hope to provide a more detailed line-by-line explanation. We will also make the...
