keras apply threshold for loss function

Question

I am developing a Keras model. My dataset is badly unbalanced, so I want to set a threshold for training and testing. If I'm not mistaken, when doing a backward propagation, neural network checks the predicted values with the original ones and calculate the error and based on the error, set new weights for neurons.

As I know, Keras uses 0.5 for the threshold. I know there are ways to apply custom metrics (as recall and precision) with custom threshold, but that threshold is only used for calculating the recall, and it is not applied in the loss function. To be more clear, If I want to set 0.85 as my threshold, the neural network would use 0.5 as threshold to calculate loss and 0.85 for recall.

Is there any ways to set this threshold for training as well?

Keras does not use any thresholds for losses. – Dr. Snoopy Aug 23 '19 at 14:09 — Dr. Snoopy, Aug 23 '19 at 14:09

score 1 · Accepted Answer · answered Aug 23 '19 at 13:41

1

There is no such a thing as a threshold for loss.

A loss function must be "differentiable", thus it must be a "continuous" function.
The best you can do is to set "class weights", such as these examples: Higher loss penalty for true non-zero predictions

answered Aug 23 '19 at 13:41

Daniel Möller

84,878
18
192
214

thanks. I didn't know that in loss funcition, the predicted values itself is used and not the rounded one. – Hamed Salimian Aug 23 '19 at 17:19

score 0 · Answer 2 · answered May 27 '21 at 08:09

In addition to class weights...

you can use metric function with the threshold parameter:
model.compile(..., metrics=[tf.keras.metrics.BinaryAccuracy(threshold=0.5)])
you can use sigmoid activation in the last layer and select after that threshold manually:

pred_labels = np.where(y_pred>0.5, 1, 0)
score = sklearn.metrics.accuracy_score(pred_labels, labels)

keras apply threshold for loss function

2 Answers2