14
12

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 5 years have passed since last update.

Keras(TensorFlowバックエンド)でMNIST(DCNN)

Posted at

KerasでMNIST(DCNN)

Kerasとは

TheanoやTensorFlowを使いやすくするためのライブラリ

Keras

実行環境

EC2(AWS)のg2.2xlargeインスタンス(オレゴン = 米国西部)
Python 2.7.6
TensorFlow 0.8.0

AWSのインスタンスは他人のAMIを使って初期化したが、自分で導入したい場合は以下を参考

EC2のGPU instanceでTensorFlow動かすのにもうソースからのビルドは必要ないっぽい?

Kerasのインストール

ドキュメントの通りにやる
TensorFlowが既にインストール済みだとして、必要に応じて'sudo'つけて

pip install scipy
pip install scikit-learn
pip install pyyaml
apt-get install libhdf5-dev
pip install h5py
pip install keras

pythonから1度

import keras

としてKerasを実行し、'~/.keras/keras.json'を以下のように編集

"backend": "theano"

"backend": "tensorflow"

コード

mnist.py
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.layers.core import Activation, Flatten, Dense
from keras.callbacks import EarlyStopping

(X_train, y_train), (X_test, y_test) = mnist.load_data()
nb_classes = 10

X_train = X_train.reshape(-1, 1, 28, 28).astype('float32')
X_test = X_test.reshape(-1, 1, 28, 28).astype('float32')
X_train /= 255
X_test /= 255
y_train = np_utils.to_categorical(y_train, nb_classes)
y_test = np_utils.to_categorical(y_test, nb_classes)

model = Sequential()

model.add(Convolution2D(nb_filter = 16, nb_row = 3, nb_col = 3, border_mode = 'same', input_shape = (1, 28, 28)))
model.add(Activation('relu'))

model.add(Convolution2D(nb_filter = 32, nb_row = 3, nb_col = 3, border_mode = 'same'))
model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size = (2, 2), border_mode = 'same'))

model.add(Convolution2D(nb_filter = 64, nb_row = 3, nb_col = 3, border_mode = 'same'))
model.add(Activation('relu'))

model.add(Convolution2D(nb_filter = 128, nb_row = 3, nb_col = 3, border_mode = 'same'))
model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size = (2, 2), border_mode = 'same'))

model.add(Flatten())

model.add(Dense(1024))
model.add(Activation('relu'))
model.add(Dense(1024))
model.add(Activation('relu'))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))

early_stopping = EarlyStopping(monitor = 'val_loss', patience = 2)

model.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
model.fit(X_train, y_train, nb_epoch = 5, batch_size = 100, callbacks = [early_stopping])
score = model.evaluate(X_test, y_test)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

参考にしたページ

深層学習ライブラリ Keras
Keras Documentation

14
12
0

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
14
12

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?