手作業で深く学ぶ(二)——多層感知機(gluon)

#  mxnet
import mxnet as mx

#  
mx.random.seed(2)

from mxnet import gluon
from mxnet import ndarray as nd
from mxnet import autograd
from mxnet import image
from utils import load_data_fashion_mnist, accuracy, evaluate_accuracy

データの取得と読み込み

#  
batch_size = 256

#  
train_data, test_data = load_data_fashion_mnist(batch_size)

モデルの定義

#  
net = gluon.nn.Sequential()

# name_scope ,  
with net.name_scope():
    net.add(gluon.nn.Flatten())
    net.add(gluon.nn.Dense(256, activation='relu'))
    net.add(gluon.nn.Dense(10))

#  
net.initialize()

Softmaxとクロスエントロピー損失関数

#  
softmax_cross_entropy = gluon.loss.SoftmaxCrossEntropyLoss()

最適化

#  
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.1})

トレーニング

#  
epochs = 5

#  
for epoch in range(epochs):
    #  
    train_loss = 0.0
    #  
    train_acc = 0.0
    #  
    for data, label in train_data:
        #  
        with autograd.record():
            #  
            output = net(data)
            #  
            loss = softmax_cross_entropy(output, label)
        #  
        loss.backward()
        #  
        trainer.step(batch_size)
        #  
        train_loss += nd.mean(loss).asscalar()
        #  
        train_acc += accuracy(output, label)

    #  
    test_acc = evaluate_accuracy(test_data, net)

    print("Epoch %d. Loss: %f, Train acc %f, Test acc %f" % (
        epoch, train_loss / len(train_data), train_acc / len(train_data), test_acc))

Epoch 0. Loss: 0.819048, Train acc 0.728666, Test acc 0.768530
Epoch 1. Loss: 0.550646, Train acc 0.808644, Test acc 0.823618
Epoch 2. Loss: 0.488554, Train acc 0.829210, Test acc 0.845553
Epoch 3. Loss: 0.457407, Train acc 0.839493, Test acc 0.842448
Epoch 4. Loss: 0.438059, Train acc 0.845486, Test acc 0.852063