Skip to content
Let's create some trippy yet artistic images using ConvNets in TensorFlow through Google's Inception Network.
Jupyter Notebook
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.ipynb_checkpoints
Boston City Flow DREAM.jpeg
Boston City Flow.jpg
Costa Rican Frog.jpg
Deep Dream with Inception Network.ipynb
LICENSE
README.md
berlin wall.jpeg
imagenet_comp_graph_label_strings.txt
inception5h.zip
scotiabank_marathon.jpg
tensorflow_inception_graph.pb

README.md

deep_dreams

This directory contains a Jupyter notebook that demonstrates how to generate trippy images using a number of Convolutional Neural Network image generation techniques implemented with TensorFlow.

  • visualizing individual feature channels and their combinations to explore the space of patterns learned by the neural network (see GoogLeNet and VGG16 galleries)
  • embedding TensorBoard graph visualizations into Jupyter notebooks
  • producing high-resolution images with tiled computation (example)
  • using Laplacian Pyramid Gradient Normalization to produce smooth and colorful visuals at low cost
  • generating DeepDream-like images with TensorFlow

You can view "deepdream.ipynb" directly on GitHub. Note that GitHub Jupyter notebook preview removes embedded graph visualizations. You can still see them online using nbviewer service.

Make sure you have all the dependencies installed.

To open the notebook, run ipython notebook command in this directory, and select 'Deep Dream with Inception Network.ipynb' in the opened browser window.

You can’t perform that action at this time.