be24159959672c32abb31697e721d96ae6ffaf97,keras/wrappers/scikit_learn.py,BaseWrapper,fit,#BaseWrapper#Any#Any#,97

Before Change

            Returns details about the training history at each epoch.
        
        if len(y.shape) == 1:
            self.classes_ = list(np.unique(y))
            if self.loss == "categorical_crossentropy":
                y = to_categorical(y)
        else:
            self.classes_ = np.arange(0, y.shape[1])

After Change

        fit_args = copy.deepcopy(self.filter_sk_params(Sequential.fit))
        fit_args.update(kwargs)

        history = self.model.fit(X, y, **fit_args)

        return history

    def filter_sk_params(self, fn, override={}):

Instances