skip-thoughts
skip-thoughts copied to clipboard
gru_layer code different from paper
The code snippet in "training/layers.py" and "skipthoughts.py" doesn't match the formulas in the paper, should it be modified as
preactx = tensor.dot(h_ * r, Ux)
preactx = preactx + xx_
@zengzhaoyang Hi,
I also found this problem when I read the code. Is there a conclusion now? Thanks.