Tianxiao Shen

Hi, Thanks for asking. I changed the original GAN loss into the non-saturating loss (i.e. min log (1-D(G(z))) -> max log D(G(z)), see the GAN paper) so it becomes more...

The noise model is from paper https://arxiv.org/pdf/1711.00043.pdf, and many other papers also found that adding noise to the input of an auto-encoder helps text generation. Your concern is definitely valid....

Can you run any other tensorflow code (say a tutorial)?

Can you run classifier.py and language_model.py in this repo? The commands are: ```bash python classifier.py --train ../data/yelp/sentiment.train --dev ../data/yelp/sentiment.dev --vocab ../tmp/yelp.vocab --model ../tmp/model.cls ``` ```bash python language_model.py --train ../data/yelp/sentiment.train.0 --dev...

Can you run the testing command (with randomly initialized model, but yelp.vocab is required): ```bash python style_transfer.py --test ../data/yelp/sentiment.test --output ../tmp/sentiment.test --vocab ../tmp/yelp.vocab ``` I haven't encountered this problem before,...

Hi, Unfortunately I think a GPU is necessary to train a model... I just uploaded a pretrained model (see the readme file and run download_model.sh), you can try it on...