Where communities thrive

Join over 1.5M+ people
Join over 100K+ communities
Free without limits
Create your own community

Explore more communities

char-rnn-tensorflow/Lobby

People

Repo info

Activity

Teknopolitica

@teknopol_twitter

(tensorflow) gambit@gambit-PC:~/rnn-tensorflow$ python sample.py§

Traceback (most recent call last):
File "sample.py", line 102, in <module>
main()
File "sample.py", line 58, in main
with open(os.path.join(args.init_dir, 'result.json'), 'r') as f:
IOError: [Errno 2] No such file or directory: 'result.json'

(after train, obvios)

@ubergarm

Teknopolitica

@teknopol_twitter

i mean, i have to create some result.json by me? and what s to write inside?

ubergarm

@ubergarm

@teknopol_twitter i'm confused, char-rnn-tensorflow/sample.py is only ~46 lines.

have you tried the latest version of the code? hash 5029173 is working fine for me and also passes travis ci build

my hunch is you're using an older version? the latest uses .pkl files not .json

also i too am a fan of Marvel's Gambit! I played that character in an RPG many years ago, haah

Ammar Asmro

@ammarasmro

Hello everyone,

How can I edit this code to do word by word predictions rather than character by character

ubergarm

@ubergarm

hello @ammarasmro

possibly read up on encoding in general e.g. character, word, or sub-word vocabulary mapping into vector space

http://colah.github.io/posts/2014-07-NLP-RNNs-Representations/#word-embeddings

ubergarm

@ubergarm

Also check how this repo does this by tokenizing the input into a fixed number of vocab: https://github.com/google/seq2seq/blob/master/docs/nmt.md#data-format

i believe char-rnn-tensorflow uses each character as one of the vocab. i haven't played around with different pre-parsers

Sébastien Rombauts

@SRombauts

Hi there! Hi @sherjilozair and @ubergarm

I am quite new on neural network, and total noob with Tensorflow.

I've found this repo and started to work with it a week ago, and would like to help improve it.

With my new eye on the subject, I could help point the few little thing that would benefit from some more polish;

Sébastien Rombauts

@SRombauts

README and cmd line help could be improved easily

some issues/PR should be closed quickly to help focus on what is useful

then we should complement the roadmap with more specific/detailed missing features

Sébastien Rombauts

@SRombauts

For instance, I believe that having some (optional) test/validation data would be nice (issue #33)

Jonathan Gan

@metamercurial

Hi, I just started playing around with char-rnn-tensorflow and was wondering why did you choose to use an encoder-decoder model along with sequence_loss_by_example? Is it also possible (and ideal) to use static_rnn and softmax cross entropy with logits respectively?

mbc

@mbcltd

Hi @sherjilozair I am playing around with the OpenAI RfR 'Train a language model on a jokes corpus' and have forked char-rnn-tensorflow to act as a starting point for playing around with the problem space. I hope this is ok, I've observed the MIT licence and kept your copyright notice

My repo is here https://github.com/mbcltd/monkhouse

mbc

@mbcltd

At the moment it's still not very funny, the best joke that it has come up with is "your mom is unit unblong?"

I wanted to say thanks for your work on this too, it's been a great starting point for generative RNNs on tensorflow

DusterJack

@DusterJack

Hi @sherjilozair ,I was running your char-rnn tensorflow could you tell me how to sample in for a specific checkpoint

GoldK9

@K9_PVP_twitter

Hello, everyone! Have someone dealt with grid-lstm for chars? I work in university and I really need vector of research on this topic. char-rnn-tensorflow (lstm) is cool, but it's not enough. Relly hope for your help, thanks!

curator23

@curator23

Hi, has anyone had success in directly replicating char-rnn? I ask because I attempted a tensorflow implementation Jan'17 but I was unable to get good output as described by char-rnn. I've only just now got Torch7 working to validate char-rnn's performance (and, indeed, it works as described). So now I can either learn Torch, or, if this project works the same way, I can continue with Tensorflow using this codebase.
Cheers!

Peter Kirn

@peterkirn

maybe this is a python 3.5.4 + windows issue here? train.py works fine, but sample.py gets lost on encoding File "C:\Users\peter\AppData\Local\Programs\Python\Python35\lib\encodings\cp437.py", line 19, in encode
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
UnicodeEncodeError: 'charmap' codec can't encode character '\xc8' in position 1: character maps to <undefined>

Peter Kirn

@peterkirn

okay - got it, seems that's in fact a 3.5 problem, solved with 3.6 :)

seems also there's a conflict on windows with CUDA support, that is 3.6 + CUDA tensorflow don't work ... but that may be a tf issue, not char-rnn

TonyWang

@tonywangcn

Hi guys, has anyone tried to transform the model to pb.model and serve it with tensorflow serving framework?

confusing about find the output node name from more than 10000 nodes name sherjilozair/char-rnn-tensorflow#122

ericliu24

@ericliu24

hi all

Yash Jakhotiya

@yashjakhotiya

Even after python3 train.py --init_from=save the model starts to train from 0. I have checkpoints saved in my save directory. Can anybody tell me what happened and how to overcome this?

Any help is appreciated

Yash Jakhotiya

@yashjakhotiya

Also it seems the training is happening on my CPU(htop shows all cores above 90%). How can I make the training run on my GPU?

Felix B.

@Gotili

hey guys. i'm wondering why we don't get any info of validation loss. it doesn't seem to be computed. how can I find out if my models are overfitting?

@yashjakhotiya you need to install the gpu version of tensorflow.