개요

가져오기

import numpy as np
from chainer import datasets, iterators
from chainer import optimizers
from chainer import Chain
from chainer import training
from chainer.training import extensions
import chainer.functions as F
import chainer.links as L
import chainer
import matplotlib.pyplot as plt

교육 데이터 세트 반복

    train, test = datasets.get_mnist()
    train = train[0 : 1000]
    train = [i[0] for i in train]

미니 배치에 대한 전처리

    train = datasets.TupleDataset(train, train)
    train_iter = iterators.SerialIterator(train, 100)
    test = test[0 : 25]

신경망의 Forward/backward 계산

class Autoencoder(Chain):
    def __init__(self):
        super(Autoencoder, self).__init__(encoder = L.Linear(784, 80), decoder = L.Linear(80, 784))
    def __call__(self, x, hidden = False):
        h = F.relu(self.encoder(x))
        if hidden:
            return h
        else:
            return F.relu(self.decoder(h))
    model = L.Classifier(Autoencoder(), lossfun = F.mean_squared_error)
    model.compute_accuracy = False

매개변수 업데이트

    optimizer = optimizers.Adam()
    optimizer.setup(model)
    updater = training.StandardUpdater(train_iter, optimizer, device = -1)
    trainer = training.Trainer(updater, (80, 'epoch'), out = "result")

    trainer.run()

평가 데이터 세트에서 현재 파라미터 평가

중간 결과를 로그에 남기기

    trainer.extend(extensions.LogReport())
    trainer.extend(extensions.PrintReport(['epoch', 'main/loss']))

결과