KerasClassifier TypeError：__call __（）在cross_val_score上正好接受2个参数（给定1个）

Question

我尝试在模型上使用cross_val_score，但出现以下错误：

Dim arrival As Date = CDate(txtArrivalDate.Text) Dim Departure As Date = CDate(txtDepartureDate.Text) Dim Days As Long = DateDiff(DateInterval.Day, arrival, Departure) Dim Total As Long = 160 * Days Dim Day As Date = arrival While (Day <= Departure) If CBool(Day.DayOfWeek.Friday And Day.DayOfWeek.Saturday) Then Total += 180 End If Day = Day.AddDays(1) End While

这是我的模特

Traceback (most recent call last):
  File "/home/dinhnha1402/.local/lib/python2.7/site-packages/keras/wrappers/scikit_learn.py", line 210, in fit
    return super(KerasClassifier, self).fit(x, y, **kwargs)
  File "/home/dinhnha1402/.local/lib/python2.7/site-packages/keras/wrappers/scikit_learn.py", line 139, in fit
    **self.filter_sk_params(self.build_fn.__call__))
TypeError: __call__() takes exactly 2 arguments (1 given)

我在任何地方（在Google上）都找不到此错误。是否有人对如何解决此问题有任何想法？

Answer 1

只需放下“（）”

那样：

分类器= KerasClassifier（build_fn = binary_classify_lstm_fc_model（），batch_size = 10，epochs = 100，verbose = 0）

======

分类器= KerasClassifier（build_fn = binary_classify_lstm_fc_model，batch_size = 10，epochs = 100，verbose = 0）

Answer 2

只需将损失从categorical_crossentropy更改为mean_squared_error。