XintianHan

It seems that there is a bug here https://github.com/lxdv/ecg-classification/blob/b13236d6114f91df3c82b2fa21b19231cc480496/models/models1d.py#L65 `F.maxpool_1d` takes kernel_size as the second parameter and stride as the third parameter. If you want to specify the stride as...

Hi. Very good implementation of URNN. I have a question. In the original paper, they said the model can be implemented in the real domain. I am wondering why your...

In Figure 6 of the paper, why are the memory usages for 7B, 13B, 33B, 65B equal to 5046M, 8476M, 19302M, 37074M, instead of 3.5 G, 6.5 G, 16.5G, 32.5G?...

Nice work! I noticed that in your code you use age_max-age to be the maximum time to event in interval censoring. However, you use age_max = 120 but age are...

Bugs in Triton operator?

1

Hi. Thanks for the nice triton implementation. Maybe I found a bug in the triton operator. It seems that the operator does not support head dim=192, but it supports dim=128...