About LayerNormLayer

[lonelywm]

in forward function, x = torch.inverse(...)

tensor = torch.FloatTensor([[1,2],[3,4]]) t_out = torch.inverse(tensor) t_o = 1/tensor print(tensor) print(t_out) print(t_o) ==========> 1 2 3 4 [torch.FloatTensor of size 2x2]

-2.0000 1.0000 1.5000 -0.5000 [torch.FloatTensor of size 2x2]

1.0000 0.5000 0.3333 0.2500 ============> or what we need is t_o in theano T.inv===1/T as has been mentioned in the paper

[github-pengge]

My bad. Now it's fixed.