why out_channels=4 * self.hidden_dim?
cuixianheng opened this issue · 2 comments
cuixianheng commented
why out_channels=4 * self.hidden_dim?
Berndinio commented
Because they split it afterwards in
cc_i, cc_f, cc_o, cc_g = torch.split(combined_conv, self.hidden_dim, dim=1)
f, g, o and g all have the same convolution operation (but with independent weights).
If you have a hidden.channel + x.channel = 4 input
ndrplz commented
Thanks @Berndinio
Also this answer might help