ALI

ALI copied to clipboard

semi-supervised learning

1

Hello,I read the paper and the source code.And it mentioned 'The last three hidden layers of the encoder as well as its output are concatenated to form a 8960-dimensional feature...

C-xiaomeng

In the decoder module. I found that z is sampled from N(0, 1), so where did you use the reparametrization trick described in formual (2) and (3) in the paper

wuhaozhe

Semi-supervised learning

7

I've been trying to reproduce your figures for semi-supervised learning on CIFAR-10 (19.98% with 1000 labels). This result is based on the technique proposed in Salimans et al. (2016), not...

christiancosgrove

I need to load a pretrained model with CPU only, but it appears the cuda arrays are serialized as such. Is there any way around this?

jcpeterson

pretrained imagenet model?

1

Could you possibly upload this or provide an external link?

jcpeterson

Preprocess_representation has a bug for me

1

Hi, I was trying to reproduce the representation learning results of paper. Everything works fine except "preprocess_representations" script. It is leading to this error: File "scripts/preprocess_representations", line 32, in preprocess_svhn...

MarziEd

I followed the same steps in the readme file, but when I run this line `$ THEANORC=theanorc python experiments/ali_cifar10.py` I get: ``` Traceback (most recent call last): File "experiments/ali_cifar10.py", line...

xtarx

Choice of Layers for Processing z in Discriminator

1

In the paper and code you used a set of 1x1 2D convolution layers to process the latent vector z in the discriminator. What was the motivation behind using 2D...

djgagne

Pre-trained models

2

Hi, I am so interested with your work, could you upload your pre-trained models (i.e., ImageNet) online ? Thanks!

jimmy-dq

sign on loss function

3

Hi, in the paper pseudocode, for Loss_d and Loss_g, the gradient ascent is turned into gradient descent by making the whole loss negative (negative signs in front of every term)....

johnwlambert