svhn semi-supervised learning vector dimensionality

9310gaurav / ali-pytorch

PyTorch implementation of Adversarially Learned Inference (BiGAN).

79 stars 11 forks source link

svhn semi-supervised learning vector dimensionality #2

Open yatindandi opened 4 years ago

yatindandi commented 4 years ago

The original ALI paper mentions 'The last three hidden layers of the encoder as well as its output are concatenated to form a 8960-dimensional feature vector.' Concatenating the output and hidden layers as you did in 'test_semisup.py' leads to a vector with lower dimensionality. Is this simply a typo in the original paper?

9310gaurav commented 4 years ago

I had this concern when I implemented the paper. The architecture is the same as mentioned in their paper and in their released Theano code. Better to check with authors but I think it's a typo in the paper.