Alfredo Canziani comments

Results 130 comments of


                                            Alfredo Canziani

Create 02-1.md

This is not finished. Why did you send a PR?

Create 02-1.md

Please, read the instructions [here](https://github.com/Atcold/pytorch-Deep-Learning/wiki/Translation-Guidelines). Namely, do not remove the English text, but enclose it in a comment block.

[ja] week05 ja translation by Jesmer Wong

Hello?

[ja] week05 ja translation by Jesmer Wong

These emails are sent through GitHub. You cannot add attachments, I don't see anything here. Please, come to GitHub and upload your contribution here, so that I can merge it...

Link is not working as expected

Thanks! The content of the linked post is the following. > It usually depends on the problem you are trying to solve. For a binary classification problem, you might want...

Link is not working as expected

Yes, please, go ahead. Then we have to track this across all languages. Comment to issue #144.

[12-regularization.ipynb] two errors happened

Thanks @norihiro-ito. @ritchieng we'll look into it.

[11-VAE.ipnb] TSNE fit_transform() happens a error with cuda

It looks good. @norihiro-ito, do you think you can send a pull request with such improvement? Otherwise @ritchieng can do it for you.

02 space stretching linear transformation should it be Y=X@W instead of [email protected]()?

I think `X` has its samples as rows. So `y = Wx` becomes `y' = x'W'`.

02 space stretching linear transformation should it be Y=X@W instead of [email protected]()?

`new_OI = OI @ W` should be `new_OI = OI @ W.t()`. The first `.t()` was a bug fix, I've merged from someone. I guess they forgot to add it...