Marc-Andre Schulz comments

Repositories
Issues
Comments

Results 4 comments of


                                            Marc-Andre Schulz

Semisup example uses 1000 instead of 100 samples

Thank you so much for your reply! And thanks for providing code examples in different frameworks! It really helps understanding your method. As I understand the code, this happens: In...

Semisup example uses 1000 instead of 100 samples

I run this: `python2.7 train_mnist_semisup.py --cost_type=VAT_finite_diff --epsilon=0.3 --layer_sizes=784-1200-1200-10 --num_labeled_samples=100` Here is what I get. What does your test error look like after 20 epochs? > [Epoch] -1 nll_train : 2.31259438679...

Semisup example uses 1000 instead of 100 samples

I am reasonably confident that the epsilon is wrong. If I increase epsilon to 4 I get better results...

Semisup example uses 1000 instead of 100 samples

I did indeed run the code on CPU. Maybe there is some bug or strange behaviour in Theano?