0
$\begingroup$

I am handling a multi-class classification problem, with label in the following form [1333201000] and the logit output of the model is in the form ([[ 0.4523, 0.0198, -0.1911, -0.0036], [ 0.4917, 0.4316, -0.2846, 0.0774], [ 0.4827, 0.2323, -0.2338, 0.2975], [ 0.0017, 0.0069, 0.1721, 0.1800], [ 0.2452, 0.0772, -0.3574, 0.1191], [ 0.2852, 0.2769, -0.0884, 0.1215], [ 0.0825, 0.2109, -0.3785, 0.0742], [ 0.2253, 0.4560, -0.1529, -0.3226], [ 0.4251, 0.0682, -0.1916, -0.2752], [ 0.3496, 0.2189, -0.1748, 0.2128]]) and the CrossEntropyLoss I use is torch.nn.crossentropyloss, I have a problem that my problem is suitable for this loss function, and is this version of torch really similar to the crossentropy function:enter image description here

Improve this question
$\endgroup$
1
  • $\begingroup$ What does it mean that you are of the form [1333201000], that the first outcome is category 1, the second is category 3, the last is category 0, etc? $\endgroup$
    – Dave
    Commented Jun 25 at 22:01

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.