Open gc625-kodifly opened 5 months ago
Sorry don't have it. I'll try training one (also with vit base).
please do :) that would be really helpful. Looking forward to the results!
@Parskatt Could you also train one using FeatUp? Would it be possible to get higher resolution outputs?
@Dawars I'm not convinced that FeatUp is useful. Would be glad to be proven wrong, but not something I'll spend time on currently.
Hi, I've modified the code to load a DinoV2 small model, but i realized that the
embed_dim
of the vit_small modelis 384, which is causing dimension mismatch problem with the RoMa ckpt provided. which assumes that the
embed_dim
is 1024. e.g.can you provide the weights for RoMa-s? As the model takes ~6GB vram even after applying the change from kde to approx_kde in #23, so being able to use a small model would help a lot