You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi,
first of all, thank you for this great project. It gives me as someone who hasn't studied machine learning the option to do some pretty nice text generation.
I trained the network on some binary data. It seems to work pretty well, or at least the loss is decreasing. Now, when I try to run sample.lua, it will give me the ordinal numbers with square brackets around it (like stored in the json file) instead of its binary counterparts.
I'm going to try to fix it myself, but I'm not a lua expert at all so I might need some help.
Also, as a feature request: What do you think about adding infinite sampling output?
The text was updated successfully, but these errors were encountered:
Hi,
first of all, thank you for this great project. It gives me as someone who hasn't studied machine learning the option to do some pretty nice text generation.
I trained the network on some binary data. It seems to work pretty well, or at least the loss is decreasing. Now, when I try to run sample.lua, it will give me the ordinal numbers with square brackets around it (like stored in the json file) instead of its binary counterparts.
I'm going to try to fix it myself, but I'm not a lua expert at all so I might need some help.
Also, as a feature request: What do you think about adding infinite sampling output?
The text was updated successfully, but these errors were encountered: