2

More than 5 years have passed since last update.

# tensorflow.jsでxor

Last updated at Posted at 2018-04-04

# 概要

tensorflow.jsでxor問題やってみた。

# サンプルコード

``````const model = tf.sequential();
units: 20,
activation: 'relu',
inputShape: [2]
}));
units: 2,
activation: 'softmax'
}));
model.compile({
loss: 'categoricalCrossentropy',
metrics: ['accuracy'],
});
const xs = tf.tensor2d([[1, 0], [0, 1], [1, 1], [0, 0]], [4, 2]);
const ys = tf.tensor2d([[1, 0], [1, 0], [0, 1], [0, 1]], [4, 2]);
model.fit(xs, ys, {
batchSize: 4,
epochs: 1000
}).then((d) => {
var str = "loss = ";
str += d.history.loss[0];
str += "<br>1, 1 = ";
var pre0 = model.predict(tf.tensor2d([1, 1], [1, 2]));
str += pre0.argMax().dataSync() + "<br>0, 0 = ";
var pre1 = model.predict(tf.tensor2d([0, 0], [1, 2]));
str += pre1.argMax().dataSync() + "<br>0, 1 = ";
var pre2 = model.predict(tf.tensor2d([0, 1], [1, 2]));
str += pre2.argMax().dataSync() + "<br>1, 0 = ";
var pre3 = model.predict(tf.tensor2d([1, 0], [1, 2]));
str += pre3.argMax().dataSync() + "<br>";
document.write(str);
});

``````

# 成果物

Register as a new user and use Qiita more conveniently

1. You get articles that match your needs
2. You can efficiently read back useful information
3. You can use dark theme
What you can do with signing up
2