69
правок
Изменения
м
Нет описания правки
# View the accuracies of the model, which is: 1 - (observations predicted wrong / total observations)
print('AccuracySingle-layer perceptron accuracy: %.2f' % accuracy_score(y_test, y_pred)) print('AccuracyMultilayer perceptron accuracy: %.2f' % accuracy_score(y_test, multi_y_pred)) Вывод: Single-layer perceptron accuracy: 0.76 Multilayer perceptron accuracy: 0.96
===Пример использования с помощью tensorflow<ref>[https://www.tensorflow.org/ Библиотека tensorflow для Python]</ref>===
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
init = tf.initialize_global_variablesinitialize_all_variables()
sess = tf.Session()
sess.run(init)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print("Accuracy: %s" % sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
Вывод:
Accuracy: 0.9164
==См. также==
