search

takerum / vat

Code for reproducing the results on the MNIST dataset in the paper "Distributional Smoothing with Virtual Adversarial Training"
110 stars 27 forks source link

Calculating Misclassification Rates on Test Set #1

Closed youralien closed 9 years ago

youralien commented 9 years ago

Would be very helpful to have code that calculates misclassification rates in a test.py script, so anyone could try to replicate the results that the paper obtained. Especially since that code must already be written!

takerum commented 9 years ago

Hi!

Thank you for the comment!

I uploaded test.py and you can obtain the error rate on test set by following commands:

python train.py <filename>
python test.py <filename>

Best,

youralien commented 9 years ago

Thanks very much :+1: Probably should update the README with this new information for anyone else!