keras multiple outputs
========================================
from keras.layers import Input, Dense
from keras.model import Model
inputs = Input(shape=(N,))
x = Dense(64, activation='relu')(inputs)
x = Dense(64, activation='relu')(x)
output1 = Dense(M, activation='softmax')(x)
output2 = Dense(M, activation='softmax')(x)
output3 = Dense(M, activation='softmax')(x)
outputk = Dense(M, activation='softmax')(x)
model = Model(input=inputs, output=[output1, output2, output3,...,outputk])
model.compile(optimizer='rmsprop',
loss='categorical_crossentorpy',
metrics=['accuracy'])
model.fit(inputData, [output1, output2, output3,.....,outputk], nb_epochs=10, batch_size=64)
========================================
댓글 없음:
댓글 쓰기