1

I am using GridSearchCV to tune the hyperparameters. I also would like to compare different metrics with each other:

def create_model(...

    model.add(Dense(,..)
    model.compile(..)
    return model

model = KerasRegressor(build_fn=create_model, verbose=0)

grid_obj  = GridSearchCV (estimator=model 
                , param_grid=hypparas
                , n_jobs=1
                , cv = 3
                , scoring = ['explained_variance', 'neg_mean_squared_error', 'r2']
                , refit = 'neg_mean_squared_error'
                , return_train_score=True
                , verbose = 2
                )

grid_result = grid_obj.fit(X_train1, y_train1)

Afai understood is that the hyperparameters are optimized such that they fit neg_mean_squared_error the best. But how can I see how the other metrics behave e.g. when evaluating? Best would be if I could compare them visually.

Ben
  • 1,432
  • 4
  • 20
  • 43

0 Answers0