write-rnn-tensorflow icon indicating copy to clipboard operation
write-rnn-tensorflow copied to clipboard

Generative Handwriting using LSTM Mixture Density Network with TensorFlow

Results 19 write-rnn-tensorflow issues
Sort by recently updated
recently updated
newest added

caveat: I'm very noob with all things machine learning as well as python I've got the sample data working just fine e.g. clone repo and run `python sample.py --filename example_name...

Hi, I have modified the code to handle another type of data where the output gaussians are uni-variate. However, I noticed while training the model that the log likelihood cost...

Hey! I hope you're having a good day. My friend and I actually implemented this as well for a final project. We were vastly impressed by some of your results...

Hi, (This is more a discussion / question than a bug.) Looks like this implementation doesn't have the attention mechanism (align to the ascii char), but still able to generate...

I installed TensorFlow with version r0.11. But there appears many mistakes while runing. Most of them are attibute errors. When I change the attribute names to old ones, it ran...

Hey, I'm new to Python as well as machine learning and couldn't find a way to solve this problem. When I run sample.py as described in the Readme, Terminal outputs...

As I followed the Readme I get an error "No such file or directory './data/strokes_training_data.cpkl'" How can I generate these training Data?

I had to copy the contents of save/ into save/save/ to get this to run. This is on OSX under TF 0.7, haven't tried it on earlier versions of TF.

``` write-rnn-tensorflow/model.py", line 50, in __init__ self.final_state = states[-1] File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/array_ops.py", line 124, in _SliceHelper raise NotImplementedError("Negative indices are currently unsupported") NotImplementedError: Negative indices are currently unsupported ``` It seems...