Closed wlgns0105 closed 6 years ago
Yes. Those are just different versions of the same paper. The 2 different error rates correspond to 2 different implementations (1 in Theano, 1 in Torch) of the same method. This git repository contains the Theano implementation. The Torch implementation is available here.
No data augmentation is used. There is only the preprocessed image dataset. If I recall correctly, we do some normalization and ZCA whitening.
Thank you for the reply
I'm trying to implement BinaryNet on PyTorch and trying to train on CIFAR-10 dataset, I have some questions
both paper writes their CIFAR-10 test error rate as 11.40% and BNN's code link goes to BinaryNet
in other words, no crop/brighten/resize etc. ? I don't understand how original CNN (10.96%) and Binarized CNN (11.40%) have same error rate...