Created by: SaviorD7

Hello everyone!

I have dataset with 8 features and 1 label column. My label could be: 1 , 2 , 3 , 4 , 5. So there are 5 different values.

I defined predict layer in my Liner Regression like that:

def lr_network(self):
        self.inputs = fluid.layers.data(
            name='x', shape=[1, 8], dtype="float32")
        self.label = fluid.layers.data(name='label', shape=[1], dtype='int64')
        self.predict = fluid.layers.fc(input=self.inputs,
                                       size=5,
                                       act='softmax')
        self.sum_cost = fluid.layers.cross_entropy(
            input=self.predict, label=self.label)
        self.accuracy = fluid.layers.accuracy(
            input=self.predict, label=self.label)
        self.loss = fluid.layers.mean(self.sum_cost)
        self.startup_program = fluid.default_startup_program()

So outputs could be only in range of 5 values.

When I am starting training I ger this:

Error: Variable value (label) of OP(fluid.layers.cross_entropy) expected >= 0 and < 5, but got 5. Please check label value. at (/paddle/paddle/fluid/operators/cross_entropy_op.h:175)
  [operator < cross_entropy2 > error]

Why?