textgenrnn
textgenrnn copied to clipboard
minimaxir
Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.
When trying to run: ```python from textgenrnn import textgenrnn ``` I get ``` Traceback (most recent call last): File "", line 1, in File "venv/env/lib/python3.7/site-packages/textgenrnn/__init__.py", line 1, in from .textgenrnn...
There is a small typo in README.md. Should read `recipes` rather than `recepies`. Semi-automated pull request generated by https://github.com/timgates42/meticulous/blob/master/docs/NOTE.md
**_This is my test script._** textgen_2 = textgenrnn(weights_path='colaboratory_weights.hdf5', vocab_path='colaboratory_vocab.json', config_path='colaboratory_config.json') generated_texts = textgen_2.generate(n=5, prefix="death", temperature=0.5, return_as_list=False) print(generated_texts) But its not generating prefix words..... for example ... death is..... death was...
If I generate a sample from model trained by `train_from_largetext_file` and use a `prefix` argument, it won't show up, if the prefix is less than `maxlen` characters (default 40). Looks...
I'm playing around with this module living in a web API where a `/train` route will train a `textgenrnn` object on some training data and then save the model weights...
Hello and good evenings, Sir. I've Installed all the required files. even h5py. but when running an example code, i get the following error: ImportError: `load_weights` requires h5py when loading...
I'm installing textgenrnn using the latest github commit (via git clone and setup.py) and after fixing some errors with the setup (tensorflow doesnt get all of the required packages) I...
Ah, nevermind. I was just using it wrong :)
I was getting a lot of CUBLAS_STATUS_ALLOC_FAILED when using my GPU and running even just this 4 line program `from textgenrnn import textgenrnn textgen = textgenrnn() textgen.train_from_file('goodcombined.txt', num_epochs=2) textgen.generate(15)` Luckily...
Is it possible that the trained model can regenerate the given input? In simple words model should produce a paraphrased version of input.
