Vadims Casecnikovs (Vadim Chashechnikov)
Vadims Casecnikovs (Vadim Chashechnikov)
After setting the source I am trying to get the duration of the audio file. Unfortunately, the answer is zero. The code: ``` await player.setSource(event.source); var duration = await player.getDuration();...
I have analyzed make_anchors function and it is very hard and wrong. If you would try to pass other size than (32,32), for example(2,2) it would show you awfull results.
Added parameter n_upsample_layers - which is the amount of upsample layers in the network. _get_last_upsample_index - is used to find stop index in iterator in Merges _get_size_change_layers_indexes - is used...
As I understand the author wants to make dynamic upsample, but the variable is never used and in code, he uses -2: -4 constants
4 here makes an incorrect understanding of using this function. So, it would be much more flexible if you need overlap to increase size to 4.
From anchors you have format cthw, but matplotlib takes tlhw, so you should at first change datasize format. ``` def cthw2tlhw(boxes): tl = boxes[:,:2] - boxes[:,2:]/2 return torch.cat([tl,boxes[:,2:]],1) ```
Hello, I've been testing WS on my dataset and on my network. I have read about std error. But even after using std = (torch.sqrt(torch.var(weight.view(weight.size(0), -1), dim=1) + 1e-12).view(-1, 1,...
# Bug report - [x] I confirm this is a bug with Supabase, not with my own application. - [x] I confirm I have searched the [Docs](https://docs.supabase.com), GitHub [Discussions](https://github.com/supabase/supabase/discussions), and...
One of the main benefits of LION, is it needs to save less data for each param. Adam needs to save Momentum and RMSProp ema's, while in LION we need...