Skip to content

Different resize option for better reproducibility #1148

Answered by rwightman
hankyul2 asked this question in General
Discussion options

You must be logged in to vote

@hankyul2 I'm aware of this but chose not to add support since it is not trivial to support properly (via pretrained default_cfg entries, arg pass through to transform factory).

I also don't agree with deviating from what has been a fairly consistent standard re ImageNet eval, especially when it doesn't preserve aspect ratios... efficientnet v2 are not the only models, the deepmind nfnet weights and convnext weights (384x384 only) also rely on different preprocess.

Something I may do in the future, but hasn't been a priority.

Replies: 1 comment 2 replies

Comment options

You must be logged in to vote
2 replies
@hankyul2
Comment options

@rwightman
Comment options

Answer selected by hankyul2
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
2 participants