wrapperband
wrapperband
I have tried multiple attempts over months to increase the depth of the nets layers (8- 10). If you watch the process seems fine with the individual training loss of...
I have returned to testing Char-rnn, hoping previous issues might be cleared up, particularly starting from checkpoints, or adding additional training data, or what settings are optimum. I am still...
I've been getting the error below with one particular (1.2MB) text file. I have traced it back (by halving the file) to some French text that was in the file....
In the Readme.md it says: Temperature. An important parameter you may want to play with is -temperature, which takes a number in range (0, 1] (0 not included), default =...
Re: " Priming. It's also possible to prime the model with some starting text using -primetext. This starts out the RNN with some hardcoded characters to warm it up with...
I've had training loss go to infinity a few times now. I thought it may have been due to bad characters, but it has now happened on, tested data, so...
https://github.com/deeplearning4j/deeplearning4j/commit/36ff5acccc3f845e6c29a16cc9b50f2bc3d576e5 Being able to auto adjust drop out (or other relevant parameters) would be advantageous for char-rnn to improve it's ability to do (consistent) "deep learning". This additional feature could...
I saw a comment on handling "words" and I also see in my training data that it would be advantageous to different temperatures whilst "considering" different scales of text. For...
It would add more flexibility in what the system could learn, if the validation could be done on a separate file. (validation / testing - excuse my ignorance of the...
I am trying to build zxipg to use in out application (Feathercoin). Something has happened in Ubuntu 16.04, where our usual build from source has failed (although we already moved...