How to interpret the probability of classes in binary classification?

[KFrank]

Hello Shaun!

@shaun

…
One point of confusion is when you say class “1”, which class are you actually referring to?
…

In short, “class ‘1’” means whatever you trained you model for it
to mean.

To explain this, let me go back to one of your earlier posts:

@shaun

Essentially, after model training during final testing, I run this piece of code:

classifier = (...)
classifier.load_state_dict(saved_model)
y_pred = classifier(x_test)
probs = torch.sigmoid(y_pred)
predicted_vals = probs > threshold

Given this code, my assumption is that predicted_vals will contain the predictions of the class labels by the model which I can then compare to y_test to get the final performance of the model.

You talk about x_test and y_test (and y_pred). I assume
that y_test is a vector of length the number of test samples,
with each value in y_test being the number 0, meaning that
this sample is in class “0”, or the number 1, meaning class “1”.
(And x_test is the input data whose classes you are trying
to predict.)

You don’t mention it, but I assume you also have an x_train
and y_train whose meanings are analogous, and that you
used x_train and y_train to train your network. The point
is that the meaning of the output of your model (whether a
given value for y_pred = classifier(x_test) means
class “0” or class “1”) depends on how you trained your model.

If you train your model with values of y_train of 1 indicating
class “1” (and feed it into BCEWithLogitsLoss) then larger
(more positive) values of y_pred will mean that you are
predicting class “1” to be more likely and smaller (more negative)
values of y_pred predict class “0” to be more likely (and
class “1” to be less likely), with the predicted probability of
class “'1” given by the sigmoid of y_pred, as discussed in
the earlier posts.

To summarize, the meaning of y_pred depends in a
straightforward way on the meaning of the y_train that you
used to train your classifier.

Best.

K. Frank