We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
allow extractor to only return embeddings, to ready for vision transf… …ormers to be used in x-clip
include tests in package for conda
add some tests
add extractor wrapper
release MobileViT, from @murufeng
add adaptive token sampling paper
make initial channels customizable for PiT
dynamic positional bias for crossformer the more efficient way as des… …cribed in appendix of paper
complete and release crossformer