KerasClassifier TypeError：__call__() 在 cross_val

Question

我尝试在我的模型上进行 cross_val_score 并收到以下错误：

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)

这是我的模型：

model = Sequential()

model.add(LSTM(int(128), input_shape=(timesteps, int(128)),return_sequences=False))

model.add(Dropout(0.2))

model.add(Dense(20, activation='relu', input_shape=(128,),kernel_initializer=initializers.glorot_uniform(seed=0)))

model.add(Dropout(0.2))

model.add(Dense(20, activation='softmax'))

model.add(Dense(2, activation='softmax')) 

model.compile(loss='categorical_crossentropy', optimizer='adam',metrics=['accuracy'])

### fit model

model.fit(X_train, Y_train, batch_size=batch_size, epochs= epochs, verbose=1, validation_data=(X_test, Y_test))

####Applying K-fold cross validation

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

accuracies = cross_val_score(estimator= classifier, X = X_train, y = Y_train, cv=10, scoring="accuracy")#n_jobs= -1

print(accuracies)

我在任何地方都找不到这个错误（在谷歌上）。有没有人对如何解决这个问题有任何想法？

Answer 1

只需将损失从 categorical_crossentropy 更改为 mean_squared_error。

Answer 2

只需删除“（）”像那样：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）