Clarification question: in the demo IPython notebook, the image transform function has the form pp_img = pp_builder.get_preprocess_fn(f'resize({RES})|value_range(-1, 1)').
Looking at the code here, this seems to be resizing an image to RES x RES (warping aspect ratio).
Is this the expected behavior? Were the SigLIP models trained with this transform (aspect ratio warping)?
Thanks for open-sourcing the SigLIP models!
Clarification question: in the demo IPython notebook, the image transform function has the form
pp_img = pp_builder.get_preprocess_fn(f'resize({RES})|value_range(-1, 1)')
.Looking at the code here, this seems to be resizing an image to
RES x RES
(warping aspect ratio).Is this the expected behavior? Were the SigLIP models trained with this transform (aspect ratio warping)?