andrewgcodes xlstm issues - Githubissues

andrewgcodes / xlstm

my attempts at implementing various bits of Sepp Hochreiter's new xLSTM architecture

MIT License

111 stars 8 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

y_pred, y_true shape, are different: loss.py:535: UserWarning: Using a target size (torch.Size([1, 1])) that is different to the input size (torch.Size([10, 1])).

#4 mw66 opened 4 days ago
1
Forget gate bias should probably be initialized to 1

#3 twoletters opened 1 month ago
1
How do I use it like LSTMLayer in torch

#2 DDCY220 opened 1 month ago
1
it = torch.exp(torch.matmul(self.wi, x) + self.bi)

#1 Tomcat099 opened 1 month ago
0