神经网络返回nan

Question

为什么有时神经网络在简单的回归任务中无法预测值并返回[nan ... nan]？

from keras.models import Sequential
from keras.layers.core import Dense, Activation, Dropout
import numpy as np
from matplotlib import pyplot as plt

X = np.asarray([1,2,3,4,5,6,7,8,9,10])
y = np.asarray([0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1])

model = Sequential()
model.add(Dense(5, input_dim=1,activation = 'linear'))
model.add(Dense(5, input_dim=1,activation = 'linear'))
model.add(Dense(1, input_dim=1,activation = 'linear'))
model.compile(loss='mse', optimizer='sgd')

model.fit(X, y, epochs=20)
X2 = np.array([10,11,12])
print(model.predict(X2))