variational-dropout-sparsifies-dnn

variational-dropout-sparsifies-dnn copied to clipboard

How to generate the dynamic image that shows the sparsity of weights through out the training as shown in README

1

Hi, may I please ask how did you generate the dynamic picture as you did in README?

jojojoshuali

Арсений, добрый день! В продолжение вчерашнего разговора: - залил форк for Python 3.5 and Theano 1.0.0 https://github.com/nnnet/Variational-dropout-sparsifies-dnn с последними Вашими коммитами - по примерам *.ipynb напишу в мессенджер

nnnet

I tried to run it on CPU: THEANO_FLAGS='floatX=float32,device=cpu,lib.cnmem=1' ipython experiments/lenet/lenet5-ard.py and got the error: lib/python2.7/site-packages/lasagne/layers/dnn.py in () 40 else: 41 raise ImportError( ---> 42 "requires GPU support -- see http://lasagne.readthedocs.org/en/"...

dongbeiwudaxian