DenseNet
DenseNet copied to clipboard
validation top1 error is odd
Hi I trained a densenet according the paper on cifar10.The top1 error of test set is odd. The result is saved in this file. net-train.pdf How can i make the top1 error curve smooth ? Thanks
Hi, have you solved the problem? I got similar trend for validation cost on cifar10 and cifar100(increase as learning rate decrease)