In [ ]:
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from sklearn import datasets, cross_validation, metrics
import chainer.functions as F
import chainer.links as L
from chainer import optimizers, Chain
from commonml.skchainer import ChainerEstimator, SoftmaxCrossEntropyClassifier
import logging
logging.basicConfig(format='%(levelname)s : %(message)s', level=logging.INFO)
logging.root.level = 20
In [ ]:
digits = datasets.load_digits()
X = digits.images
y = digits.target
In [ ]:
X = X.reshape((len(X), 1, 8, 8))
In [ ]:
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y,
test_size=0.2,
random_state=42)
In [ ]:
class Model(Chain):
def __init__(self):
super(Model, self).__init__(conv1=F.Convolution2D(1, 12, 3),
l2=L.Linear(6*3*12, 10),
)
def __call__(self, x):
h1 = F.max_pooling_2d(F.relu(self.conv1(x)), (1, 2))
h2 = self.l2(h1)
return h2
classifier = ChainerEstimator(model=SoftmaxCrossEntropyClassifier(Model()),
optimizer=optimizers.AdaGrad(lr=0.05),
batch_size=128,
device=0,
stop_trigger=(100, 'epoch'))
classifier.fit(X_train, y_train)
score = metrics.accuracy_score(y_test, classifier.predict(X_test))
print('Test Accuracy: {0:f}'.format(score))