Public | Automated Build

Last pushed: 3 years ago
Short Description
Short description is empty for this repo.
Full Description

Dockerized deepdream: Generate ConvNet Art in the Cloud

Google recently released the
deepdream software package for generating images like

which uses the Caffe Deep Learning
Library and a cool iPython notebook example.

Setting up Caffe, Python, and all of the required dependencies is not
trivial if you haven't done it before! More importantly, a GPU isn't
required if you're willing to wait a couple of seconds for the images
to be generated.

Let's make it brain-dead simple to launch your very own
deepdreaming server (in the cloud, on an Ubuntu machine, Mac via
Docker, and maybe even Windows if you try out Kitematic by Docker)!


I decided to create a self-contained Caffe+GoogLeNet+Deepdream Docker image
which has everything you need to generate your own deepdream art. In
order to make the Docker image very portable, it uses the CPU version
of Caffe and comes bundled with the GoogLeNet model.

The compilation procedure was done on Docker Hub and for advanced
users, the final image can be pulled down via:

docker pull visionai/clouddream

The docker image is 2.5GB, but it contains a precompiled version of
Caffe, all of the python dependencies, as well as the pretrained
GoogLeNet model.

For those of you who are new to Docker, I hope you will pick up some
valuable engineering skills and tips along the way. Docker makes it very easy
to bundle complex software. If you're somebody like me who likes a
clean Mac OS X on a personal laptop, and do the heavy-lifting in the
cloud, then read on.

# Instructions

We will be monitoring the `inputs` directory for source images and
dumping results into the `outputs` directory.  Nginx (also inside a
Docker container) will be used to serve the resulting files and a
simple AngularJS GUI to render the images in a webpage.


You've launched a Cloud instance using a VPS provider like
DigitalOcean and this instance has Docker running. If you don't know
about DigitalOcean, then you should give them a try.  You can lauch a
Docker-ready cloud instance in a few minutes.  If you're going to set
up a new DigitalOcean account, consider using my referral link:

Will need an instance with at least 1GB of RAM for processing small output images.

Let's say our cloud instance is at the address and we set it
up so that it contains our SSH key for passwordless log-in.

ssh root@
git clone
cd clouddream

To make sure everything is working properly you can do 

docker ps

You should see three running containers: deepdream-json, deepdream-compute, and deepdream-files

root@deepdream:~/clouddream# docker ps
21d495211abf ubuntu:14.04 "/bin/bash -c 'cd /o 7 minutes ago Up 7 minutes deepdream-json
7dda17dafa5a visionai/clouddream "/bin/bash -c 'cd /o 7 minutes ago Up 7 minutes deepdream-compute
010427d8c7c2 nginx "nginx -g 'daemon of 7 minutes ago Up 7 minutes>80/tcp, 443/tcp deepdream-files

If you want to stop the processing, just run:


If you want to jump inside the container to debug something, just run:

cd /opt/deepdream

#This will take input.jpg, run deepdream, and write output.jpg

## Feeding images into deepdream

From your local machine you can just scp images into the `inputs`
directory inside deepdream as follows:

From your local machine

scp images/*jpg root@

## Instructions for Mac OS X and boot2docker

First, install boot2docker.  Now start boot2docker.

boot2docker start

My boot2docker on Mac returns something like this:

Waiting for VM and Docker daemon to start...
Writing /Users/tomasz/.boot2docker/certs/boot2docker-vm/ca.pem
Writing /Users/tomasz/.boot2docker/certs/boot2docker-vm/cert.pem
Writing /Users/tomasz/.boot2docker/certs/boot2docker-vm/key.pem

To connect the Docker client to the Docker daemon, please set:
export DOCKER_HOST=tcp://
export DOCKER_CERT_PATH=/Users/tomasz/.boot2docker/certs/boot2docker-vm

So I simply paste the last three lines (the ones starting with export)
right into the terminal.

export DOCKER_HOST=tcp://
export DOCKER_CERT_PATH=/Users/tomasz/.boot2docker/certs/boot2docker-vm

Keep this IP address in mind. For me it is ``.

NOTE: if running a `docker ps` command fails at this point and it says
something about certificates, you can try:

boot2docker ssh sudo /etc/init.d/docker restart

Now proceed just like you're in a Linux environment.

cd ~/projects
git clone
cd clouddream

You should now be able to visit `` in your browser.

## Processing a YouTube video

If don't have your own source of cool jpg images to process, or simply
want to see what the output looks like on a youtube video, I've
included a short `` script which does all the work for you.

If you want to start processing the "Charlie Bit My Finger" video, simply run:


And then visit the `` URL to see the frames show up
as they are being processed one by one. The final result will be
writen to ``

Here are some frames from the
[Daft Punk - Pentatonix](

![deepdreaming Pentatonix](

## Navigating the Image Gallery

You should now be able to visit `` in your browser and
see the resulting images appear in a nicely formatted mobile-ready grid.

You can also show only `N` images by changing to the URL so something like this:

And instead of showing random `N` images, you can view the latest images:

You can view the processing log here:

You can view the current image being processed:

You can view the current settings:

Here is a screenshot of what things should look like when using the 'conv2/3x3' setting:
![deepdreaming Dali](

And if you instead use the 'inception_4c/output' setting:
![deepdreaming Dali](

Additionally, you can browse some more cool images on the
[]( server, which I've
currently configured to run deepdream through some Dali art. When you
go to the page, just hit refresh to see more goodies.

### User contributed DeepDream images

Several people ran their own experiments on different images and
different layers. For example, @ihaventkilledanybodysince1984 shows an
example of different layer effects on a frog drawing.

![deepdream frog](
Check out the [frog face effect gallery on imgur](

### Changing image size and processing layer

Inside deepdream/settings.json you'll find a settings file that looks like this:
    "maxwidth" : 400,
    "layer" : "inception_4c/output"

You can change maxwidth to something larger like 1000 if you want
big output images for big input images, remeber that will you need more RAM memory
for processing lager images. For testing maxwidth of 200
will give you results much faster. If you change the settings and
want to regenerate outputs for your input images, simply remove the
contents of the outputs directory:

rm deepdream/outputs/*

Possible values for layer are as follows. They come from the
tmp.prototxt file which lists the layers of the GoogLeNet network used
in this demo. Note that the ReLU and Dropout layers are not valid for deepdreaming.



The final GUI is based on


The included Dockerfile is an extended version of

Which is a modification from the original Caffe CPU master Dockerfile tleyden:

This dockerfile uses the deepdream code from:


MIT License. Have fun. Never stop learning.

The team

Docker Pull Command
Source Repository