準備¶
Googleドライブのマウント¶
In [2]:
from google.colab import drive
drive.mount('/content/drive')
sys.pathの設定¶
以下では，Googleドライブのマイドライブ直下にDNN_codeフォルダを置くことを仮定しています．必要に応じて，パスを変更してください．
In [3]:
import sys
sys.path.append('/content/drive/My Drive/DNN_code_colab_ver200425')
keras¶
線形回帰¶
In [2]:
pip install tensorflow==1.15
In [3]:
pip install keras==2.3.1
In [1]:
import tensorflow as tf
# logging levelを変更
tf.logging.set_verbosity(tf.logging.ERROR)
import numpy as np
import matplotlib.pyplot as plt
iters_num = 1000
plot_interval = 10
x = np.linspace(-1, 1, 200)
np.random.shuffle(x)
d = 0.5 * x + 2 + np.random.normal(0, 0.05, (200,))
from keras.models import Sequential
from keras.layers import Dense
# モデルを作成
model = Sequential()
#model.add(Dense(input_dim=1, units=1))
model.add(Dense(input_dim=1, output_dim=1))
# モデルを表示
model.summary()
# モデルのコンパイル
model.compile(loss='mse', optimizer='sgd')
# train
for i in range(iters_num):
loss = model.train_on_batch(x, d)
if (i+1) % plot_interval == 0:
print('Generation: ' + str(i+1) + '. 誤差 = ' + str(loss))
W, b = model.layers[0].get_weights()
print('W:', W)
print('b:', b)
y = model.predict(x)
plt.scatter(x, d)
plt.plot(x, y)
plt.show()
In [15]:
import tensorflow as tf
# logging levelを変更
tf.logging.set_verbosity(tf.logging.ERROR)
# モジュール読み込み
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Activation
from keras.optimizers import SGD
# 乱数を固定値で初期化
np.random.seed(1)
# シグモイドの単純パーセプトロン作成
model = Sequential()
model.add(Dense(input_dim=2, output_dim=1))
model.add(Activation('sigmoid'))
model.summary()
model.compile(loss='binary_crossentropy', optimizer=SGD(lr=0.1))
# トレーニング用入力 X と正解データ T
X = np.array( [[0,0], [0,1], [1,0], [1,1]] )
T = np.array( [[0], [1], [1], [1]] ) #OR
#T = np.array( [[0], [1], [1], [0]] ) #XOR
#T = np.array( [[0], [0], [0], [1]] ) #AND
# トレーニング
model.fit(X, T, epochs=300, batch_size=10)
# トレーニングの入力を流用して実際に分類
Y = model.predict_classes(X, batch_size=10)
print("TEST")
print(Y == T)
In [36]:
import tensorflow as tf
# logging levelを変更
tf.logging.set_verbosity(tf.logging.ERROR)
import matplotlib.pyplot as plt
from sklearn import datasets
iris = datasets.load_iris()
x = iris.data
d = iris.target
# from sklearn.cross_validation import train_test_split
from sklearn.model_selection import train_test_split
x_train, x_test, d_train, d_test = train_test_split(x, d, test_size=0.2)
from keras.models import Sequential
from keras.layers import Dense, Activation
from keras.optimizers import SGD
#モデルの設定
model = Sequential()
model.add(Dense(12, input_dim=4))
#model.add(Activation('relu'))
model.add(Activation('sigmoid'))
model.add(Dense(3, input_dim=12))
model.add(Activation('softmax'))
model.summary()
model.compile(optimizer=SGD(lr=0.1), loss='sparse_categorical_crossentropy', metrics=['accuracy'])
history = model.fit(x_train, d_train, batch_size=5, epochs=20, verbose=1, validation_data=(x_test, d_test))
loss = model.evaluate(x_test, d_test, verbose=0)
#Accuracy
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.ylim(0, 1.0)
plt.show()
In [41]:
import tensorflow as tf
# logging levelを変更
tf.logging.set_verbosity(tf.logging.ERROR)
# 必要なライブラリのインポート
import keras
import matplotlib.pyplot as plt
from data.mnist import load_mnist
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True, one_hot_label=True)
# 必要なライブラリのインポート、最適化手法はAdamを使う
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.optimizers import Adam
# モデル作成
model = Sequential()
model.add(Dense(512, activation='relu', input_shape=(784,)))
model.add(Dropout(0.2))
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(10, activation='softmax'))
model.summary()
# バッチサイズ、エポック数
batch_size = 128
epochs = 20
model.compile(loss='sparse_categorical_crossentropy',
optimizer=Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0, amsgrad=False),
metrics=['accuracy'])
history = model.fit(x_train, d_train, batch_size=batch_size, epochs=epochs, verbose=1, validation_data=(x_test, d_test))
loss = model.evaluate(x_test, d_test, verbose=0)
print('Test loss:', loss[0])
print('Test accuracy:', loss[1])
#Accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
# plt.ylim(0, 1.0)
plt.show()
In [54]:
import tensorflow as tf
# logging levelを変更
tf.logging.set_verbosity(tf.logging.ERROR)
# 必要なライブラリのインポート
import keras
import matplotlib.pyplot as plt
from keras.datasets import mnist
from data.mnist import load_mnist
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True, one_hot_label=False)
# 行列として入力するための加工
batch_size = 128
num_classes = 10
epochs = 20
img_rows, img_cols = 28, 28
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
# 必要なライブラリのインポート、最適化手法はAdamを使う
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.optimizers import Adam
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.summary()
# バッチサイズ、エポック数
batch_size = 128
epochs = 20
model.compile(loss='sparse_categorical_crossentropy', optimizer=Adam(learning_rate=0.001, beta_1=0.0001, beta_2=0.99, amsgrad=False), metrics=['accuracy'])
history = model.fit(x_train, d_train, batch_size=batch_size, epochs=epochs, verbose=1, validation_data=(x_test, d_test))
#Accuracy
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
# plt.ylim(0, 1.0)
plt.show()
cifar10¶
実行に時間がかかるため割愛¶
データセット cifar10
32x32ピクセルのカラー画像データ
10種のラベル「飛行機、自動車、鳥、猫、鹿、犬、蛙、馬、船、トラック」
トレーニングデータ数:50000, テストデータ数:10000
http://www.cs.toronto.edu/~kriz/cifar.html
In [51]:
import tensorflow as tf
# logging levelを変更
tf.logging.set_verbosity(tf.logging.ERROR)
#CIFAR-10のデータセットのインポート
from keras.datasets import cifar10
(x_train, d_train), (x_test, d_test) = cifar10.load_data()
#CIFAR-10の正規化
from keras.utils import to_categorical
# 特徴量の正規化
x_train = x_train/255.
x_test = x_test/255.
# クラスラベルの1-hotベクトル化
d_train = to_categorical(d_train, 10)
d_test = to_categorical(d_test, 10)
# CNNの構築
import keras
from keras.models import Sequential
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.layers.core import Dense, Dropout, Activation, Flatten
import numpy as np
model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same',input_shape=x_train.shape[1:]))
model.add(Activation('relu'))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(10))
model.add(Activation('softmax'))
# コンパイル
model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
#訓練
history = model.fit(x_train, d_train, epochs=20)
# モデルの保存
model.save('./CIFAR-10.h5')
#評価 & 評価結果出力
print(model.evaluate(x_test, d_test))
[try]¶
- RNNの出力ノード数を128に変更
- RNNの出力活性化関数を sigmoid に変更
- RNNの出力活性化関数を tanh に変更
- 最適化方法をadamに変更
- RNNの入力 Dropout を0.5に設定
- RNNの再帰 Dropout を0.3に設定
- RNNのunrollをTrueに設定
In [64]:
import tensorflow as tf
# logging levelを変更
tf.logging.set_verbosity(tf.logging.ERROR)
import numpy as np
import matplotlib.pyplot as plt
import keras
from keras.models import Sequential
from keras.layers.core import Dense, Dropout,Activation
from keras.layers.wrappers import TimeDistributed
from keras.optimizers import SGD
from keras.layers.recurrent import SimpleRNN, LSTM, GRU
# データを用意
# 2進数の桁数
binary_dim = 8
# 最大値 + 1
largest_number = pow(2, binary_dim)
# largest_numberまで2進数を用意
binary = np.unpackbits(np.array([range(largest_number)], dtype=np.uint8).T,axis=1)[:, ::-1]
# A, B初期化 (a + b = d)
a_int = np.random.randint(largest_number/2, size=20000)
a_bin = binary[a_int] # binary encoding
b_int = np.random.randint(largest_number/2, size=20000)
b_bin = binary[b_int] # binary encoding
x_int = []
x_bin = []
for i in range(10000):
x_int.append(np.array([a_int[i], b_int[i]]).T)
x_bin.append(np.array([a_bin[i], b_bin[i]]).T)
x_int_test = []
x_bin_test = []
for i in range(10001, 20000):
x_int_test.append(np.array([a_int[i], b_int[i]]).T)
x_bin_test.append(np.array([a_bin[i], b_bin[i]]).T)
x_int = np.array(x_int)
x_bin = np.array(x_bin)
x_int_test = np.array(x_int_test)
x_bin_test = np.array(x_bin_test)
# 正解データ
d_int = a_int + b_int
d_bin = binary[d_int][0:10000]
d_bin_test = binary[d_int][10001:20000]
model = Sequential()
model.add(SimpleRNN(units=16,
return_sequences=True,
input_shape=[8, 2],
go_backwards=False,
activation='sigmoid',
#activation='tanh',
#dropout=0.5,
recurrent_dropout=0.3,
unroll = True,
))
# 出力層
model.add(Dense(1, activation='sigmoid', input_shape=(-1,2)))
model.summary()
model.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy'])
# model.compile(loss='mse', optimizer='adam', metrics=['accuracy'])
history = model.fit(x_bin, d_bin.reshape(-1, 8, 1), epochs=5, batch_size=2)
# テスト結果出力
score = model.evaluate(x_bin_test, d_bin_test.reshape(-1,8,1), verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
In [ ]: