Zhuang Liu

@shicai Thanks for sharing, we have added the link on our readme page. Hope more people start using them:)

I think that is totally acceptable, sometimes the variance on CIFAR-100 can be even up to 1% (when error around ~25% ).

Maybe first try a lower learning rate. If it doesn't work, see if other network architectures don't work either. Then make the decision on whether to use this network, or...

1. We didn't meet the same problem training on CIFAR-100. I think on SVHN similar things happened, but the increase is not as significant as this. 2. Our validation loss...

Did you use data augmentation? (Padding, cropping and flipping on input image). If you didn't, it could overfit on training set and the test loss could increase.

Thanks for your interest in DenseNet. We are experimenting on ImageNet with different model sizes. Right now we have some preliminary results (relatively small models), which is shown in the...

@baiyancheng20 sorry this is trained using torch. If you want to use them we can give you torch model definitions first (or pre-trained models later). Model definition here: [densenet-imagenet.txt](https://github.com/liuzhuang13/DenseNet/files/546310/densenet-imagenet.txt) After...

@baiyancheng20 Thanks for your interest. In order to get better performance, you may want to adapt the caffe code for CIFAR a little bit according to the differences I listed...

Sorry, the file was wrong, it was probably an older version. I'll correct it. Sorry but I couldn't remember whether this would make a big difference. Also, there was pretrained...

Hi, @nihalgoalla please check https://github.com/liuzhuang13/DenseNetCaffe (for CIFAR, without BC structure) and https://github.com/shicai/DenseNet-Caffe (for ImageNet).