I tried to reproduce Wide-DenseNet-BC results on cifar10, but got 0.5% more than your error about densenet HOT 4 CLOSED

One difference I noted is that you normalize the input by dividing 255, but we normalize the input by channel means and stds, that might be a difference.

https://github.com/liuzhuang13/DenseNet/blob/master/datasets/cifar10.lua#L37

from densenet.

I noted the data augmentation in your code is significantly different, I think you can refer to this code for data augmentation in keras, https://github.com/robertomest/convnet-study/blob/master/train.py

from densenet.

Thank you very much for your check and reply!
I will follow it(however, I think my input norm and aug are reasonable... :P ) and update to you once I get the result.

Have a good weekend!

from densenet.

I updated https://github.com/seasonyc/densenet/blob/master/cifar10-test.py
at https://github.com/seasonyc/densenet/blob/571b0d6d3873fbec3eec9e631370e74172d05a4b/cifar10-test.py#L51
and https://github.com/seasonyc/densenet/blob/571b0d6d3873fbec3eec9e631370e74172d05a4b/cifar10-test.py#L141

The validation acc has some promotion, now the top acc is 95.64%. I think it's acceptable although it still has a bit gap than yours.

Thanks
YC

from densenet.