33
$\begingroup$

Which is better for accuracy or are they the same? Of course, if you use categorical_crossentropy you use one hot encoding, and if you use sparse_categorical_crossentropy you encode as normal integers. Additionally, when is one better than the other?

$\endgroup$
37
$\begingroup$

Use sparse categorical crossentropy when your classes are mutually exclusive (e.g. when each sample belongs exactly to one class) and categorical crossentropy when one sample can have multiple classes or labels are soft probabilities (like [0.5, 0.3, 0.2]).

Formula for categorical crossentropy (S - samples, C - classess, $s \in c $ - sample belongs to class c) is:

$$ -\frac{1}{N} \sum_{s\in S} \sum_{c \in C} 1_{s\in c} log {p(s \in c)} $$

For case when classes are exclusive, you don't need to sum over them - for each sample only non-zero value is just $-log p(s \in c)$ for true class c.

This allows to conserve time and memory. Consider case of 10000 classes when they are mutually exclusive - just 1 log instead of summing up 10000 for each sample, just one integer instead of 10000 floats.

Formula is the same in both cases, so no impact on accuracy should be there.

| improve this answer | |
$\endgroup$
  • 1
    $\begingroup$ Do they impact the accuracy differently, for example on mnist digits dataset? $\endgroup$ – Master M Dec 1 '18 at 8:47
  • 1
    $\begingroup$ Mathematically there is no difference. If there is significant difference in values computed by implementations (say tensorflow or pytorch), then this sounds like a bug. Simple comparison on random data (1000 classes, 10 000 samples) show no difference. $\endgroup$ – frenzykryger Dec 1 '18 at 14:20
  • $\begingroup$ Dear frenzykryger, I guess you forgot a minus for the one sample case only: "for each sample only non-zero value is just -log(p(s $\in$ c))". For the rest, nice answer. $\endgroup$ – Nicg Sep 13 '19 at 12:48
  • $\begingroup$ You're right. Thanks! $\endgroup$ – frenzykryger Sep 14 '19 at 13:54
  • $\begingroup$ @frenzykryger I am working on multi-output problem. I have 3 seperate output o1,o2,o3 and each one have 167,11,7 classes respectively. I've read your answer that it'll make no difference but is there any difference if I use sparse__ or not. Can I go for categorical for the last 2 and sparse for the first one as there are 167 classes in the first class? $\endgroup$ – Deshwal Jan 8 at 4:58
13
$\begingroup$

The Answer, In a Nutshell

If your targets are one-hot encoded, use categorical_crossentropy. Examples of one-hot encodings:

[1,0,0]
[0,1,0] 
[0,0,1]

But if your targets are integers, use sparse_categorical_crossentropy. Examples of integer encodings (for the sake of completion):

1
2
3
| improve this answer | |
$\endgroup$
  • 1
    $\begingroup$ Do I need a single output node for sparse_categorical_crossentropy? And what does the from_logits argument mean? $\endgroup$ – Leevo Dec 15 '19 at 17:01

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.