Updates:
- Added support for batch size>1 on a single image parameter + objective (
AutoImageParam
now has a new argbatch_size
which defaults to1
). This would lead to higher quality visualizations with a smaller number of iterations. - Fix unintended
PytorchVersionError
on torch2.x
. Thanks @matthiasgeihs 🙌
Interface change:
The input (layer_outputs
) in custom objective functions is not anymore a list of tensors of shape (c, h, w)
. It's now a list of tensors of shape (n, c, h, w)
where n
= batch size. (The same applies for other shapes of intermediate layer outputs (...) -> (n, ...)
)