This repository has been archived by the owner on Aug 1, 2024. It is now read-only.
Did you ever train with the ViTC? #63
Comments
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Hey,
Thanks for sharing such a great work. Digging into the code, I've noticed that there is a ConvEmbed layer from this paper implemented in the vision transformer. I was wondering whether you had a chance to train with this layer, taking into account that masking is not as straightforward as with the common PatchEmbed.
Thanks,
Carlos
The text was updated successfully, but these errors were encountered: