allenhung1025

I have the same doubt, too.

Hi, you can make target and input last dimension(dim=2) the same size

@RussellSB Hi, for Example, if the target size is (torch.Size([64, 80, 51])) and the input size is (torch.Size([64, 80, 40])), you can compute loss between target[:, :, :40] and input.

我也有这个问题，大家解决了吗

Hi @afiaka87, When I use `-e` flag, it doesn't work. May you explain more about how you specify GPU rank on multi-gpu systems?

Hi @afiaka87, When I was trying to run this [model](https://replicate.com/allenhung1025/looptest) on multi-gpu systems, I got some error `Starting Docker image cog-looptest-base and running setup()... docker: Error response from daemon: could...

已經解決了，沒有下載完全的檔案

> > 已經解決了，沒有下載完全的檔案 > > 这个是什么意思，没下载全解密文件还是模型文件？ 沒有下載模型完全

Thanks for your feedback. I understood blur functions more. However, I still didn't understand why, in your implementation, you used the blurring technique two times. The first time is in...