Kyungsu Kim

Results 2 issues of Kyungsu Kim

According to the following visualization of dilated causal convolutional layers, I think strides in the conv1d (after time_to_batch) should be 2(equal to the dilation) so that there is only minimum...

Hi, I got interested in your paper and I really wanted to try the ImageNet results on my own machine. However, I found that the pre-trained parameters data are missing...