pannous
pannous
1-d dilated/atrous convolution is the way to go ...
strange, maybe a tflearn.py bug? we'll investigate ...
Sorry I can NOT reproduce the error with any version of tensorflow / tflearn :( maybe try pip install git+https://github.com/tflearn/tflearn.git pip3 install git+https://github.com/tflearn/tflearn.git
strange. tried most combinations of py2.7 / py3.5 tf0.11.0 / 0.12.0rc1 tflearn-0.2.2 tflearn-0.1.1(?) mac / ubuntu only getting warnings, no errors
at this point it might be easiest if you just patch tflearn/helpers/trainer.py, line 125 manually
or file a tflearn bug astonishing how many people here seem to be affected. or just skip the toy examples and jump straight to ./densenet_layer.py
do `git clone --recursive https://github.com/pannous/tensorflow-speech-recognition` or `pip install layer`
problem confirmed. In the meantime do git **recursive** : `git clone --recursive https://github.com/pannous/tensorflow-speech-recognition` then you should see: ``` tensorflow-speech-recognition/layer$ ls baselines.py Clockwork_RNN.py __init__.py net.py old README.md setup.py tensorboard_util.py ```
`pip install --upgrade layer` should now work
Dropbox blocked that file, but you can generate it yourself. Look at ./generate_speech_data.py if you are on a Mac, the same approach would also work on other systems.