ハイパーパラメータのチューニング

Kerasで学ぶIntroduction to Deep Learning

Miguel Esteban

Data Scientist & Founder

ニューラルネットのハイパーパラメータ

  • 層の数
  • 1層あたりのニューロン数
  • 層の順序
  • 層の活性化関数
  • バッチサイズ
  • 学習率
  • オプティマイザ
Kerasで学ぶIntroduction to Deep Learning

Sklearnの復習

# Import RandomizedSearchCV
from sklearn.model_selection import RandomizedSearchCV

# Instantiate your classifier tree = DecisionTreeClassifier()
# Define a series of parameters to look over params = {'max_depth':[3,None], "max_features":range(1,4), 'min_samples_leaf': range(1,4)}
# Perform random search with cross validation tree_cv = RandomizedSearchCV(tree, params, cv=5)
tree_cv.fit(X,y) # Print the best parameters print(tree_cv.best_params_)
{'min_samples_leaf': 1, 'max_features': 3, 'max_depth': 3}
Kerasで学ぶIntroduction to Deep Learning

KerasモデルをSklearn推定器にする

# Function that creates our Keras model
def create_model(optimizer='adam', activation='relu'):
    model = Sequential()
    model.add(Dense(16, input_shape=(2,), activation=activation))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(optimizer=optimizer, loss='binary_crossentropy')
    return model

# Import sklearn wrapper from keras from tensorflow.keras.wrappers.scikit_learn import KerasClassifier
# Create a model as a sklearn estimator model = KerasClassifier(build_fn=create_model, epochs=6, batch_size=16)
Kerasで学ぶIntroduction to Deep Learning

交差検証

# Import cross_val_score
from sklearn.model_selection import cross_val_score

# Check how your keras model performs with 5 fold crossvalidation
kfold = cross_val_score(model, X, y, cv=5)


# Print the mean accuracy per fold kfold.mean()
0.913333
# Print the standard deviation per fold
kfold.std()
0.110754

Kerasで学ぶIntroduction to Deep Learning

NNハイパーパラメータ調整のコツ

  • グリッドサーチよりランダムサーチが有利
  • エポックは多くしない
  • データセットは小さめのサンプルで
  • バッチサイズ・活性化関数・オプティマイザ・学習率を試す
Kerasで学ぶIntroduction to Deep Learning

Kerasモデルでのランダムサーチ

# Define a series of parameters
params = dict(optimizer=['sgd', 'adam'], epochs=3, 
              batch_size=[5, 10, 20], activation=['relu','tanh'])

# Create a random search cv object and fit it to the data random_search = RandomizedSearchCV(model, params_dist=params, cv=3)
random_search_results = random_search.fit(X, y)
# Print results print("Best: %f using %s".format(random_search_results.best_score_, random_search_results.best_params_))
Best: 0.94 using {'optimizer': 'adam', 'epochs': 3, 'batch_size': 10, 'activation': 'relu'}
Kerasで学ぶIntroduction to Deep Learning

他のハイパーパラメータの調整

def create_model(nl=1,nn=256):
    model = Sequential()
    model.add(Dense(16, input_shape=(2,), activation='relu'))

# Add as many hidden layers as specified in nl for i in range(nl): # Layers have nn neurons model.add(Dense(nn, activation='relu')) # End defining and compiling your model...
Kerasで学ぶIntroduction to Deep Learning

他のハイパーパラメータの調整

# Define parameters, named just like in create_model()
params = dict(nl=[1, 2, 9], nn=[128,256,1000])

# Repeat the random search...

# Print results...
Best: 0.87 using {'nl': 2,'nn': 128}
Kerasで学ぶIntroduction to Deep Learning

ネットワークをチューニングしましょう!

Kerasで学ぶIntroduction to Deep Learning

Preparing Video For Download...