Replies: 1 comment 1 reply
-
OK, finally done keras_cv_attention_models/gpvit. Such an complicated model! |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Recently another nice work has been published on Non-Hierachical Vision Transformer. It would be nice to have an implementation here.
code: https://github.com/ChenhongyiYang/GPViT
paper: https://arxiv.org/pdf/2212.06795.pdf
Beta Was this translation helpful? Give feedback.
All reactions