I was wondering, how are biases initialized in pytorch for the linear layer? I inspected it out of curiosity and it seems randn(0,1) would be my guess:
>>> l = torch.nn.Linear(3,2)
>>> l.bias
Parameter containing:
0.2137
0.0904
[torch.FloatTensor of size 2]
l = nn.Linear(3, 2)
l.bias.data.normal_(0, 1)
l.bias.data.fill_(0)
3 Likes
How is that different from using:
torch.nn.init.constant
?
also how did u find out about these methods like fill_ and normal_? It doesn’t seem to me that they are super well documented (sort of mysterious how people even know how to do these things)
also is there anything wrong with doing:
x = torch.FloatTensor(3,2)
l.bias.data = x
obviously assuming x is the initialization that we might want.
Whats the difference?
http://pytorch.org/docs/master/tensors.html you can check it in doc, maybe using torch.nn.init is no difference