Phil Wang
hmm, i think the GC should handle this?
@wytcsuch sure, I can probably offer a similar interface what is `dst_latents` vs `src_latents`?
@wytcsuch ok, it's much clearer to me now yup, i'll provide you an API similar to the official repo soon
@wytcsuch https://github.com/lucidrains/stylegan2-pytorch#coding let me know if that works for you
@gamladz more data and higher augmentation probability!
@harsh-agarwal hi! sure! I was thinking perhaps an integration with https://github.com/aimhubio/aim ?
@harsh-agarwal would just the G and D losses be good enough for you to begin with?
PL kicks in around 5000 steps (at least, it should) I'll see what I can do!
https://github.com/lucidrains/stylegan2-pytorch/tree/1.5.0#logging-to-experiment-tracker let me know if that works for you! @harsh-agarwal
@Zenahr Hi! Would you like to give v1.0 a try? It may have been how I had packaged the script