KerasClassifier inside new class not functioning correctly - keras

Question

I am using KerasClassifier to create a NN, usually, after using .fit() the object will still retain type of wrappers.scikit_learn.KerasClassifier and then further functions such as cross_val_score and GridSearchCV work perfectly. I am now trying to fit my code into a format that I have been given for a project which has a predefined class to hold the NN. When trying to assign either this new class or a property of the class with the KerasClassifier wrapper type the return from .fit() is instead of type engine.sequential.Sequential meaning the further functions will not operate.
I would expect the .fit() function to return an item of type KerasClassifier.
The code below is passed preprocessed training data.
class Module4_Model:
def __init__(self):
self.my_model = None
def init_classifier(self):
self.my_model = KerasClassifier(build_fn = self.build_classifier,
optimizer = 'adam',
n_units = 7,
batch_size = 32,
epochs = 100)
return self.my_model
def build_classifier(self, optimizer, n_units):
self.my_model = Sequential()
self.my_model.add(Dense(units = n_units, kernel_initializer = 'uniform', activation = 'relu', input_dim = 15))
self.my_model.add(Dense(units = n_units, kernel_initializer = 'uniform', activation = 'relu'))
self.my_model.add(Dense(units = 1, kernel_initializer = 'uniform', activation = 'sigmoid'))
self.my_model.compile(optimizer = optimizer, loss = 'binary_crossentropy', metrics = ['accuracy'])
return self.my_model
def train_model(self, X_train, y_train):
history = self.my_model.fit(X_train, y_train, validation_split = 0.1)
print(type(self.my_model))
return history
my_model = Module4_Model()
my_model.init_classifier()
history = my_model.train_model(x_train_processed, y_train_processed)
The same code moved outside of a class works as expected.

Answer 1

The problem is that you are using the same variable (self.my_model) inside both init_classifier and build_classifier, which is not necessary at all. When the KerasClassifier instance is created, it received self.build_classifier, which is called each time a new classifier instance is created (inside KerasClassifier), and then it overwrites the value of self.my_model.
A simple solution is to do this:
def build_classifier(self, optimizer, n_units):
model = Sequential()
model.add(Dense(units = n_units, kernel_initializer = 'uniform', activation = 'relu', input_dim = 15))
model.add(Dense(units = n_units, kernel_initializer = 'uniform', activation = 'relu'))
model.add(Dense(units = 1, kernel_initializer = 'uniform', activation = 'sigmoid'))
model.compile(optimizer = optimizer, loss = 'binary_crossentropy', metrics = ['accuracy'])
return model
Just do not use the same variable for two purposes and it should be fine.