This is the python wrapper for libartificial.
It is CPU (OpenBLAS) implemented but soon with support for cuBLAS if I get my hands on an NVIDIA GPU. I have plans to extend it for CNNs and RNNs.
The feedforward procedure does not have a hardcoded depth (it can have as many layers as you want).
The library is created with Linux machines in mind but OSX users should not have a problem if they have gcc installed. To compile the library with Visual Studio you need to do a whole lot of processing to build OpenBLAS yourself and include the pthreads.dll in your build system but I do not recommend it.
In order to get and build libartificial you have to do the following (assuming working installation of git)
git clone https://github.com/fetacore/libartificial.git
cd libartificial
rm -rf .git
make cpu
mv libartificial.* ../
cd ../
rm -rf libartificial
After that get the python wrapper
git clone https://github.com/fetacore/python-libartificial.git
cd python-libartificial
rm -rf .git
mv ../libartificial.* libartificial/shared/libartificial.so
Afterwards, create a python virtual environment and put the whole folder "libartificial" inside <virtualenv_folder>/lib/python3.6/site-packages and you are done!
In order to compile the library for CPU you need to install OpenBLAS.
If you like my work and/or you want to use it for your own projects or want me to create a custom recipe for you, I would gladly accept your donations at:
BTC: 1HzxXZPQSNg7U53XoBSWCpugKUg5DaZELu
ETH: 0xf09fce52f7ecd940cae2826deae151b6495354f6
Copyright (c) Jim Karoukis. This project is licensed under the MIT License - see the LICENSE file for details.