anibali / infogan Goto Github PK

A couple of strange things: 1) it pauses/hangs for a very long time before starting training, 2) output images (continuous variable) are 280x140 (I expected square 280x280), and the reproduction is certainly not approaching parity with the training data (this is image 50).

Maybe 50 epochs (the default) is too few? But still, the shape seems odd... It seems like there's still a bug somewhere.

[EDIT: Sorry, I just noticed that the images on your git page are actually 5x10 digits. So the output is probably correct. I guess it's just a question of whether 50 is too few epochs.]

other dataset such as celebA will train a result?

Do you mean the number of z and c is 74，the first 2 value of the gen-inputs is the salient-vars, am i right?
thank you

/root/torch/install/bin/luajit: /root/torch/install/share/lua/5.1/trepl/init.lua:384: /root/torch/install/share/lua/5.1/trepl/init.lua:384: loop or previous error loading module 'cudnn'

cudnn is up and running on the machine for vanilla tensorflow.