CODEWITHSUNDEEP
scikit-learnlstmadaboost
Wanan
Wanan

Reputation: 11

What should I do in order to use LSTM as a weak learner for adaboostregressor

The specific implementation of base_estimator is not mentioned in the sklearn documentation. I want to use LSTM as base_estimator of adaboostregressor, but the way in the picture doesn't work, how can I design LSTM as base_estimator? Thank you all.

# This is my model
model = Sequential()
model.add(LSTM(128, return_sequences=False))
model.add(Dropout(0.2))
model.add( Dense(64,activation = 'relu'))
model.add(Dropout(0.3))
model.add( Dense(32,activation = 'relu'))
model.add(Dropout(0.3))
model.add( Dense(8,activation = 'relu'))
model.add(Dropout(0.3))
model.add(Dense(1))
model.compile(optimizer=Adam(lr =0.0003),
              loss='mean_squared_error')


from sklearn.ensemble import AdaBoostRegressor
regr = AdaBoostRegressor(base_estimator=model, n_estimators=5, random_state=1)

I tried to assign 'model' to 'base_estimator'. But it reported an error. Here are the errors.

TypeError: Cannot clone object '<tensorflow.python.keras.engine.sequential.Sequential object at 0x7f972c2982e0>' 
(type <class 'tensorflow.python.keras.engine.sequential.Sequential'>):
 it does not seem to be a scikit-learn estimator as it does not implement a 'get_params' method.

I don't know how to implement this LSTM as a base_estimator.

Upvotes: 1

Views: 106

Answers (0)

Related Questions