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:
from conx import Network, SGD
dataset = [[[0, 0], [0]],
[[0, 1], [1]],
[[1, 0], [1]],
[[1, 1], [0]]]
net = 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)
net.test()Creates dynamic, rendered visualizations like this:
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 first. For example, on Ubuntu or other Debian-based system:
sudo apt install libffi-dev libffi6Next, 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 -UYou 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 theanoor
pip install tensorflowOn MacOS, you may also need to render the SVG visualizations:
brew install cairoTo make MP4 movies, you will need the ffmpeg executable installed and available on your default path.
On MacOS, you could use:
brew install ffmpegOn Windows:
See, for example, https://github.com/adaptlearning/adapt_authoring/wiki/Installing-FFmpeg
On Linux:
sudo apt install ffmpeg
# or perhaps:
sudo yum install ffmpegUse with Jupyter Notebooks
To use the Network.dashboard() and camera functions, you will need to install and enable ipywidgets:
With pip:
pip install ipywidgets
jupyter nbextension enable --py widgetsnbextensionWith conda
conda install -c conda-forge ipywidgetsInstalling ipywidgets with conda will also enable the extension for you.
Changing Keras Backends
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"
}Examples
See the notebooks folder and the documentation for additional examples.
Differences with Keras
Conx does not allow targets to be a single value. Keras will automatically turn single values into a onehot encoded vectors. In conx, you should just convert such “labels” into their encodings before training.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file conx-3.5.11.tar.gz.
File metadata
- Download URL: conx-3.5.11.tar.gz
- Upload date:
- Size: 71.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 9f290f237f74fff50958c1f8c997c50b31e7e01da26ff4c43ffb68b226a9d2f3 |
|
| MD5 | ff9962a5ea2d5d5daacfc43048ddb8a0 |
|
| BLAKE2b-256 | dd788a6490fbd904239af623a324e734771a1212e10185a96aa20b9dc47afab4 |
File details
Details for the file conx-3.5.11-py2.py3-none-any.whl.
File metadata
- Download URL: conx-3.5.11-py2.py3-none-any.whl
- Upload date:
- Size: 78.2 kB
- Tags: Python 2, Python 3
- Uploaded using Trusted Publishing? No
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 9e5a54bf11399fbdba2cbff978149950f2770eb77666d6c1e82d765e961ac56c |
|
| MD5 | 48eb6c8c66c042627589719ac727f8af |
|
| BLAKE2b-256 | 9b9a0a3dff6309a02d71f4f546434b8dd3882885865794c8ec108f75819cdf22 |
