Takeru Miyato
Takeru Miyato
Hi, thanks for your attention. We will release the source code for reproducing the results, after the notification of the decision (and we may create another repository for the code).
Hi, we have uploaded the code of ResNet for ImageNet: https://github.com/pfnet-research/sngan_projection. Please look at the code if you are interested in. Thanks,
Sorry for the late reply. All scores showed in README (except for the scores in the "official" column) are calculated with the code in this repository. The scores for each...
Also, thank you for your comments. Now I'm preparing the codes on ipython notebook to easily reproduce the results. I will let you know as soon as I upload the...
I ran the code with the default value in the README just now, and I confirmed that it achieves ~2.0 % test error rate with 100 labeled examples, which is...
Ah, that's right, I will take a look at the code again and I will let you know the update here. Thanks for telling me that!
Hi, I ran with 100 labeled examples and I got 2.08% test error rate. How do you run the code? I use theano v0.9 on GPU.
I am sorry for the late reply. Do you happen to run the code on CPU? I found that the results on CPU and GPU are different, (I had never...
I am not sure... anyway, thanks for reporting the results on CPU! Would you tell me the final accuracy with epsilon=4 on CPU?
Hi, You use the same instance of `nn.BatchNorm2d` within different layers. I am not familiar with PyTorch implementation of BN well, but I think you should use a different instance...