Inference for Deep Ensemble

[psteinb]

Hi @mvaldenegro -
I returned to this repo to prepare some examples for a lecture series I am giving. When I went through your code, I stumbled to this line:
https://github.com/mvaldenegro/keras-uncertainty/blob/42f50a36c70003b16b7f343002766708ad2a289a/keras_uncertainty/models/DeepEnsembleClassifier.py#L219C1-L220C73

predictions = np.concatenate(predictions)
mean_pred = np.mean(predictions, axis=0)
mean_pred = mean_pred / np.sum(mean_pred, axis=1, keepdims=True)

according to the DeepEnsemble paper, one should average the predicted probabilities in the classification case. I guess, that is the line which instantiates the variable mean_pred. But I am a bit lost, why you "normalize" this again in the last line of the excerpt above. Can you comment please?

[mvaldenegro]

Hey @psteinb
Because sometimes you would get probabilities that sum to 0.99 or even 0.98, due to numerical error and rounding, this way you make sure probabilities sum to 1.0