Skip to main content
This is a pre-production deployment of Warehouse. Changes made here affect the production instance of PyPI (pypi.python.org).
Help us improve Python packaging - Donate today!

On-Ramp to Deep Learning. Built on Keras

Project Description

The On-Ramp to Deep Learning

Built in Python 3 on Keras 2.

Read the documentation at conx.readthedocs.io

Ask questions on the mailing list: conx-users

Implements Deep Learning neural network algorithms using a simple interface with easy visualizations and useful analytical. Built on top of Keras, which can use either TensorFlow, Theano, or CNTK.

The network is specified to the constructor by providing sizes. For example, Network(“XOR”, 2, 5, 1) specifies a network named “XOR” with a 2-node input layer, 5-unit hidden layer, and a 1-unit output layer.

Example

Computing XOR via a target function:

import conx as cx

dataset = [[[0, 0], [0]],
           [[0, 1], [1]],
           [[1, 0], [1]],
           [[1, 1], [0]]]

net = cx.Network("XOR", 2, 5, 1, activation="sigmoid")
net.set_dataset(dataset)
net.compile(error='mean_squared_error',
            optimizer="sgd", lr=0.3, momentum=0.9)
net.train(2000, report_rate=10, accuracy=1.0)
net.test(show=True)

Creates dynamic, rendered visualizations like this:

Don’t Install

Rather than installing conx, consider one of the following pre-built options:

Install

conx requires Python3, Keras version 2.0.8 or greater, and some other Python modules that are installed automatically with pip.

On Linux, you may need to install libffi and libffi-dev in order to render layers for the network display. If you attempt to display a network and it appears empty, or if you attempt to network.propagate_to_image() and it gives a PIL error, you need these libraries.

On Ubuntu or other Debian-based system:

sudo apt install libffi-dev libffi6

Next, we use pip to install the Python packages.

Note: you may need to use pip3, or admin privileges (eg, sudo), or install into a user environment.

pip install conx -U

You will need to decide whether to use Theano, TensorFlow, or CNTK. Pick one. See docs.microsoft.com for installing CNTK on Windows or Linux. All platforms can also install either of the others using pip:

pip install theano

or

pip install tensorflow

On MacOS, you may also need to render the SVG visualizations:

brew install cairo

To make MP4 movies, you will need the ffmpeg executable installed and available on your default path.

On MacOS, you could use:

brew install ffmpeg

On Windows:

See, for example, https://github.com/adaptlearning/adapt_authoring/wiki/Installing-FFmpeg

On Linux:

sudo apt install ffmpeg
# or perhaps:
sudo yum install ffmpeg

Use with Jupyter Notebooks

To use the Network.dashboard() and camera functions, you will need to enable ipywidgets:

jupyter nbextension enable --py widgetsnbextension

If you install via conda, then it will already be enabled:

conda install -c conda-forge ipywidgets

Setting the Keras Backend

To use a Keras backend other than TensorFlow, edit (or create) ~/.keras/kerson.json, like:

{
    "backend": "theano",
    "image_data_format": "channels_last",
    "epsilon": 1e-07,
    "floatx": "float32"
}

Troubleshooting

  1. If you have a problem after installing matplotlib with pip, and you already have matplotlib installed (say, with apt) you may want to remove the apt-installed version of matplotlib.
  2. Theano has many known problems. Don’t use Theano, use TensorFlow.

Examples

See the notebooks folder and the documentation for additional examples.

Release History

This version
History Node

3.6.0

History Node

3.5.100

History Node

3.5.99

History Node

3.5.20

History Node

3.5.19

History Node

3.5.18

History Node

3.5.17

History Node

3.5.16

History Node

3.5.15

History Node

3.5.14

History Node

3.5.13

History Node

3.5.12

History Node

3.5.11

History Node

3.5.10

History Node

3.5.9

History Node

3.5.8

History Node

3.5.7

History Node

3.5.6

History Node

3.5.5

History Node

3.5.4

History Node

3.5.3

History Node

3.5.2

History Node

3.5.1

History Node

3.5.0

History Node

3.4.3

History Node

3.4.2

History Node

3.4.1

History Node

3.4.0

History Node

3.3.5

History Node

3.3.4

History Node

3.3.3

History Node

3.3.2

History Node

3.3.1

History Node

3.3.0

History Node

3.2.4

History Node

3.2.2

History Node

3.2.1

History Node

3.2.0

History Node

3.1.3

History Node

3.1.2

History Node

3.1.1

History Node

3.1.0

History Node

3.0.3

History Node

3.0.2

History Node

3.0.1

History Node

3.0.0

History Node

1.0.3

History Node

1.0.2

History Node

1.0.1

History Node

1.0.0

History Node

0.2.0

History Node

0.1.0

History Node

0.0.4

History Node

0.0.3

History Node

0.0.2

History Node

0.0.1

Download Files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

File Name & Hash SHA256 Hash Help Version File Type Upload Date
conx-3.6.0-py2.py3-none-any.whl
(90.5 kB) Copy SHA256 Hash SHA256
py2.py3 Wheel Feb 12, 2018
conx-3.6.0.tar.gz
(83.8 kB) Copy SHA256 Hash SHA256
Source Feb 12, 2018

Supported By

WebFaction WebFaction Technical Writing Elastic Elastic Search Pingdom Pingdom Monitoring Dyn Dyn DNS Sentry Sentry Error Logging CloudAMQP CloudAMQP RabbitMQ Heroku Heroku PaaS Kabu Creative Kabu Creative UX & Design Fastly Fastly CDN DigiCert DigiCert EV Certificate Rackspace Rackspace Cloud Servers DreamHost DreamHost Log Hosting