Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two
1.62k
stars
220
forks
source link
Executing with a trailing \ in the arguments sets the variable new to the truthy value '\\' and deletes all progress #139
Open
jonas-klesen opened 1 year ago
A rather frustrating issue:
calling it with a trailing \ like lightweight_gan --data full_cleaned256/ --name c256 --models_dir models --results_dir results \
sets the variable new to the truthy value '\' and deletes all progress.
This might well be an issue with Fire but might be mitigated or fixed here too, I am unsure about that.
Thanks. Jonas