我想使用包含正负连续值的数据集来测试使用keras的NN模型.keras模型如下:
from keras.models import Sequential
from keras.layers import Dense
import numpy
#fix random seed for reproducibility
numpy.random.seed(7)
#load and read dataset
dataset = numpy.loadtxt("Phenols-toxicity.csv", delimiter=";")
# split into input (X) and output (Y) variables
X = dataset[:,2:4]
Y = dataset[:,1]
print ("Variables: \n", X)
print ("Target_outputs: \n", Y)
# create model
model = Sequential()
model.add(Dense(4, input_dim=2, activation='relu'))
#model.add(Dense(4, activation='relu'))
model.add(Dense(1, activation='relu'))
model.summary()
# Compile model
model.compile(loss='mean_squared_error', optimizer='sgd', metrics=['MSE'])
# Fit the model
model.fit(X, Y, epochs=500, batch_size=10)
#make predictions (test)
F …