Question

我需要对LSTM使用Bagging方法，对时间序列数据进行培训。我已经定义了模型库，并使用KerasRegressor链接到scikit-learn。但是具有AttributeError：'KerasRegressor'对象没有属性'loss'。我该如何解决？

更新：我使用了Manoj Mohan的方法（在第一个评论中），并且在拟合步骤中成功了。但是，当我将Manoj Mohan的类修改为

时，就会出现TypeError问题。

class MyKerasRegressor(KerasRegressor): 
    def fit(self, x, y, **kwargs):
        x = np.expand_dims(x, -2)
        super().fit(x, y, **kwargs)

    def predict(self, x, **kwargs):
        x = np.expand_dims(x, -2)
        super().predict(x, **kwargs)

它解决了与（.fit（））相同的predict（）的尺寸问题。问题是：

TypeError                                 Traceback (most recent call last)
<ipython-input-84-68d76cb73e8b> in <module>
----> 1 pred_bag = bagging_model.predict(x_test)
TypeError: unsupported operand type(s) for +: 'int' and 'NoneType'

完整脚本：

def model_base_LSTM():

    model_cii = Sequential()

    # Make layers
    model_cii.add(CuDNNLSTM(50, return_sequences=True,input_shape=((1, 20))))
    model_cii.add(Dropout(0.4))

    model_cii.add(CuDNNLSTM(50, return_sequences=True))
    model_cii.add(Dropout(0.4))

    model_cii.add(CuDNNLSTM(50, return_sequences=True))
    model_cii.add(Dropout(0.4))

    model_cii.add(CuDNNLSTM(50, return_sequences=True))
    model_cii.add(Dropout(0.4))

    model_cii.add(Flatten())
    # Output layer
    model_cii.add(Dense(1))

    # Compile
    model_cii.compile(optimizer = 'adam', loss = 'mean_squared_error', metrics=['accuracy'])

    return model_cii

model = MyKerasRegressor(build_fn = model_base_LSTM, epochs=100, batch_size =70)
bagging_model = BaggingRegressor(base_estimator=model, n_estimators=10)
train_model = bagging_model.fit(x_train, y_train)

bagging_model.predict(x_test)

Output:
TypeError                                 Traceback (most recent call last)
<ipython-input-84-68d76cb73e8b> in <module>
----> 1 pred_bag = bagging_model.predict(x_test)
TypeError: unsupported operand type(s) for +: 'int' and 'NoneType'

Answer 1

model_base_LSTM()方法中有错误。替换

return model

与

return model_cii

修复“检查输入时出错”的错误，可以添加一个额外的尺寸。这也解决了scikit-learn（2维）与Keras LSTM（3维）问题。创建KerasRegressor的子类来处理尺寸不匹配。

class MyKerasRegressor(KerasRegressor):
    def fit(self, x, y, **kwargs):
        x = np.expand_dims(x, -2)
        return super().fit(x, y, **kwargs)

    def predict(self, x, **kwargs):
        x = np.expand_dims(x, -2)
        return super().predict(x, **kwargs)

model = MyKerasRegressor(build_fn = model_base_LSTM, epochs=100, batch_size =70)

处理Bagging方法时，如何解决TypeError：+不支持的操作数类型：“ int”和“ NoneType”

1 个答案: