Adam
Adam
Also want to be able to continue from a given point. I tried just now, after training for 100 epoch, starting at 101, it appears to have started from scratch...
Ah figured this out; you can set the path to the previous weights (generator and discriminator), using the input parameters in the train.py file, lines 35 to 51
I also see very high memory usage of daskframe. If I read a file with on disk size 2.7G, htop tells me I'm using 14.1G (RES), more than I expect...