gnn 1.1.7

Graph Neural Network Tensorflow implementation

This repo contains a Tensorflow implementation of the Graph Neural Network model.

• Website (including documentation): https://mtiezzi.github.io/gnn_site/

Install

Requirements

The GNN framework requires the packages tensorflow, numpy, scipy.

To install the requirements you can use the following command

pip install -U -r requirements.txt

Install the latest version of GNN:

pip install gnn

For additional details, please see Install.

Simple usage example

import gnn.GNN as GNN
import gnn.gnn_utils
import Net as n

# Provide your own functions to generate input data
inp, arcnode, nodegraph, labels = set_load()

# Create the state transition function, output function, loss function and  metrics
net = n.Net(input_dim, state_dim, output_dim)

# Create the graph neural network model
g = GNN.GNN(net, input_dim, output_dim, state_dim)

#Training

for j in range(0, num_epoch):
    g.Train(inp, arcnode, labels, count, nodegraph)

    # Validate
    print(g.Validate(inp_val, arcnode_val, labels_val, count, nodegraph_val))

License

Released under the 3-Clause BSD license (see LICENSE.txt):

Copyright (C) 2004-2019 Matteo Tiezzi
Matteo Tiezzi <[e-mail]>
Alberto Rossi <[e-mail]>