Increasing the batch size for xgboost #1719
Unanswered
EvanGertis
asked this question in
Q&A
Replies: 1 comment
-
Hi @EvanGertis The ValueError provides already a good part of the explanation, for 1D feature vectors the implementation has only been tested for a batch size of 1. It should be possible to run the algorithm for 1D feature vectors but additional validation might likely be needed. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I am using the ART example for implementing xgboost. I'd like to increase the
batch_size
to improve the generated adversarial examples.Can someone explain why I am receiving this error when I try to increase the
batch_size
?Beta Was this translation helpful? Give feedback.
All reactions