はじめに 前回はGraphNetを使って「とにかく5を出力する」ように学習しました。今回は、ノードやエッジの値を足し算する学習をしてみようと思います。 環境などは前回と同じです。 import numpy as np import sonnet as snt import graph_nets as gn import tensorflow as tf import matplotlib.pyplot as plt from pprint import pprint %matplotlib inline tf.reset_default_graph() def create_data_dict(n0=0., n1=0., e0=0., e1=0.): data_dict = dict( nodes=[[n0], [n1], [0.]], # node attrs (n0, n1, n2)
![GraphNetを使って足し算を学習する - Qiita](https://cdn-ak-scissors.b.st-hatena.com/image/square/7fbe9a011005c8d8319e09af7354daeb05c335b5/height=288;version=1;width=512/https%3A%2F%2Fqiita-user-contents.imgix.net%2Fhttps%253A%252F%252Fcdn.qiita.com%252Fassets%252Fpublic%252Farticle-ogp-background-412672c5f0600ab9a64263b751f1bc81.png%3Fixlib%3Drb-4.0.0%26w%3D1200%26mark64%3DaHR0cHM6Ly9xaWl0YS11c2VyLWNvbnRlbnRzLmltZ2l4Lm5ldC9-dGV4dD9peGxpYj1yYi00LjAuMCZ3PTk3MiZoPTM3OCZ0eHQ9R3JhcGhOZXQlRTMlODIlOTIlRTQlQkQlQkYlRTMlODElQTMlRTMlODElQTYlRTglQjYlQjMlRTMlODElOTclRTclQUUlOTclRTMlODIlOTIlRTUlQUQlQTYlRTclQkYlOTIlRTMlODElOTklRTMlODIlOEImdHh0LWFsaWduPWxlZnQlMkN0b3AmdHh0LWNvbG9yPSUyMzIxMjEyMSZ0eHQtZm9udD1IaXJhZ2lubyUyMFNhbnMlMjBXNiZ0eHQtc2l6ZT01NiZzPWYyNmY0ZmUyZmZmN2IyNGEzZDc1ODM4YzQ0MGQ1ODk0%26mark-x%3D142%26mark-y%3D57%26blend64%3DaHR0cHM6Ly9xaWl0YS11c2VyLWNvbnRlbnRzLmltZ2l4Lm5ldC9-dGV4dD9peGxpYj1yYi00LjAuMCZoPTc2Jnc9NzcwJnR4dD0lNDBtb2tlbW9rZWNoaWNrZW4mdHh0LWNvbG9yPSUyMzIxMjEyMSZ0eHQtZm9udD1IaXJhZ2lubyUyMFNhbnMlMjBXNiZ0eHQtc2l6ZT0zNiZ0eHQtYWxpZ249bGVmdCUyQ3RvcCZzPWE3YmE0M2YzZTNjMmFjNmNkMmYyNDI2ZmVkM2FhYzU4%26blend-x%3D142%26blend-y%3D436%26blend-mode%3Dnormal%26txt64%3DaW4g5qCq5byP5Lya56S-U3Byb2NrZXQ%26txt-width%3D770%26txt-clip%3Dend%252Cellipsis%26txt-color%3D%2523212121%26txt-font%3DHiragino%2520Sans%2520W6%26txt-size%3D36%26txt-x%3D156%26txt-y%3D536%26s%3Dacdffe7b5861137451621c122555142f)