Grace Luo
Grace Luo
Additionally, what is the intuition for detaching the fake output when training the discriminator ([see code](https://github.com/TencentARC/GFPGAN/blob/9c3f2d62cb4e63a7ba7ce68648dd1667b2b2ef44/gfpgan/models/gfpgan_model.py#L420))?
Thanks Alasdair! That resolved the issue. Another question, I'm getting this warning and I'm wondering if it's safe to ignore: ``` /opt/conda/conda-bld/pytorch_1591914855613/work/aten/src/ATen/native/cuda/RangeFactories.cu:239: UserWarning: The number of elements in the out...
Might be worth giving users more control over the all semesters option or listing the semester's we're averaging for better transparency.
@LEON-MING this should be fixed in master; I believe the fix is changing the line to `courseCardProps as any` (weird Typescript stuff)