This repository has the code from my O'Reilly article 'Visualizing Convolutional Neural Networks w/ TensorFlow' published on.
This code contains tools for building a dataset and a jupyter notebook for implementing and visualizing a simple convolutional neural network.
There are three ways you can install these packages: by using Docker, by using Anaconda Python, or installing the packages manually yourself. Though not required if you have a NVidia graphic card with a compute capability of 3.0 or greater and atleast 3gb of memory using GPU supported TensorFlow will drasticallly improve preformance. Instructions for installing GPU supported TensorFlow can be found here.
-
Download and install Docker. If using Ubuntu 14.04/16.04 I wrote my own instructions for installing docker here.
-
Download and unzip this entire repo from GitHub, either interactively, or by entering
git clone https://github.com/wagonhelm/Visualizing-Convnets.git
-
Open your terminal and use
cd
to navigate into the directory of the repo on your machinecd Visualizing-Convnets
-
To build the Dockerfile, enter
docker build -t cnn_dockerfile -f dockerfile .
If you get a permissions error on running this command, you may need to run it with
sudo
:sudo docker build -t cnn_dockerfile -f dockerfile .
-
Run Docker from the Dockerfile you've just built
docker run -it -p 8888:8888 -p 6006:6006 cnn_dockerfile bash
or
sudo docker run -it -p 8888:8888 -p 6006:6006 cnn_dockerfile bash
if you run into permission problems.
-
Launch Jupyter and Tensorboard both by using tmux
tmux jupyter notebook --allow-root
Press CTL+B
thenC
to open a new tmux window, thentensorboard --logdir='/tmp/cnn'
To switch windows
Press CTL+B
thenwindow #
Once both jupyter and tensorboard are running, using your browser, navigate to the URLs shown in the terminal output if those don't work try http://localhost:8888/ for Jupyter Notebook and http://localhost:6006/ for Tensorboard.