about concat #4
Comments
Hi Chen, |
I have some of my own opinions, which may be to save code complexity and the number of parameters |
@automan000 Guess you have referenced some implementations of LSTM instead of convLSTM, note the difference of formulas of them . |
@Jackie-Chou Actually I am referring the implementations such as BasicConvLSTMCell |
Bug fixed. Close this issue. |
https://arxiv.org/pdf/1506.04214.pdf
in this parper
the LSTM compute i(t),f(t),o(t) is use x(t),h(t-1) and c(t-1). but in your code convolution_lstm.py line 24:
combined = torch.cat((input, h), dim=1)
you just use x and h, why?
The text was updated successfully, but these errors were encountered: