wrapperband

The problem seems to be in /CharSplitLMMinibatchLoader.lua On these lines : -- perform safety checks on split_fractions assert(split_fractions[1] >= 0 and split_fractions[1] = 0 and split_fractions[2] = 0 and split_fractions[3]

I'm pretty sure I wouldn't even know how to do that? (store a number over 127 in a signed byte) I tested this sort of problem with char-rnn by removing...

I can look more into it (char-rnn) after the holidays. but for example (thanks for the info re: print) input text 2.9MB, data 2.9MB vocab 2.4kb text 6MB data 6MB...

Cheers for that. I've moved to the new rig, with the R9 280, which has been flaky. I'll copy over a checkpoint from the old PC, and run it. Char-rnn...

From what I can see char-rnn learns characters are grouped into "words" in from a relatively small amount of sample text (about 1 MB). Which is one reason I think...

That's a neat word pre-processing function. Can you train on characters, then switch to words? Wouldn't it be possible to "train" the character net to do the word processing? Would...

Just want to say thanks, will test it on my problems / experiments. note it says Use the -usewords 1 in the your docs (not -wordlevel 1)

Thanks, this looks like what was causing my "bug", (which was well discouraging) , where training loss kept going to infinity, even with new data.. I'll retest, and see if...

Thanks for the update, sounds like the new inputs also caused me some of the problems. But I always created new data.tz and vocab.t7 for updated input, so that didn't.

I'm setting up a new PC, with R9 290, which might be causing other problems, 15.10. Bearing that in mind, I tested the udibr's development version and got the same...