kdyang

Could you please upload the results on cifar10? Did you reproduce the results in the paper?

Could you please provide the training detail of the SE-WRN for cifar? Thanks a lot!

About the result of PyramidNet-110 baseline in the paper

1

In the [paper](https://arxiv.org/abs/1905.04899?context=cs.CV) (table 6), PyramidNet-110 without cutmix is reported to achieve 19.85% top1 error on CIFAR100. Since in the [paper](https://arxiv.org/abs/1610.02915) of PyramidNet, the error rate with the same setting...

First of all, thans for your work! The latest labelme add 'goup' keyword to indicate seperated parts for the same instance. But as I annotate the images and convert the...

BTW, we should use preact (resnet -V2 style), rather than post-act(V1 style).

According to the definition of momentum in keras doc, the momentum of BN layers should be 0.9, which is not the default momentum value of BN layer of pytorch (0.1).

Have you tried applying time schedule to improve the performance as in the article?

In the function `create_wide_residual_network`, ``` x = initial_conv(ip) nb_conv = 4 ``` After the `initial_conv`, why the nb_conv equals 4 rather than 1?

As the titile.

First of all, thanks for such great work! And I have a question about data used in this work. In the paper "k-t NEXT: Dynamic MR Image Reconstruction Exploiting Spatio-temporal...