이진 분류

Keras로 시작하는 딥 러닝

Miguel Esteban

Data Scientist & Founder

이진 분류는 언제 사용하나요?

데이터셋

페어플롯

import seaborn as sns

# Plot a pairplot
sns.pairplot(circles, hue="target")

시그모이드 함수

구축해 봅시다

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

# Instantiate a sequential model
model = Sequential()

구축해 봅시다

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

# Instantiate a sequential model
model = Sequential()

# Add input and hidden layer
model.add(Dense(4, input_shape=(2,),
                activation='tanh'))

구축해 봅시다

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

# Instantiate a sequential model
model = Sequential()

# Add input and hidden layer
model.add(Dense(4, input_shape=(2,),
                activation='tanh'))

# Add output layer, use sigmoid
model.add(Dense(1, 
                activation='sigmoid'))

컴파일, 학습, 예측

# Compile model
model.compile(optimizer='sgd',
              loss='binary_crossentropy')

# Train model
model.train(coordinates, labels, epochs=20)

# Predict with trained model
preds = model.predict(coordinates)

연습해 봅시다!

Keras로 시작하는 딥 러닝