Second last tilmestep as the c_t in the baseline model?
KinWaiCheuk opened this issue · 0 comments
KinWaiCheuk commented
At Line 310, you have the following code
output, hidden = self.gru(forward_seq, hidden) # output size e.g. 8*100*256
c_t = output[:,t_samples,:].view(batch, 256) # c_t e.g. size 8*256
So you are using the second last timestep as c_t
? Since the last timestep should be output[:,t_samples+1,:]
, or just simply hidden
.
As far as I understand from the original paper, c_t
should be the last timestep. Am I missing anything here?