New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
questions about initializing the lstm hidden states #25
Comments
Isn't show attend tell in the same file the one you want? |
@ruotianluo |
Intialize with zero. |
@ruotianluo |
The zero-th are bos. |
@ruotianluo |
start token. |
@ruotianluo |
@ruotianluo |
mask would be 1,1,1,1,0 |
@ruotianluo |
Outputs are softmax probabilities. |
@ruotianluo |
You have to modify the crit. It's nontrivial. |
@ruotianluo |
I see what you mean. I misunderstood. Yeah, it should work. |
here :https://github.com/ruotianluo/neuraltalk2.pytorch/blob/master/models/OldModel.py#L49
you seems to directly init the hidden states with the fc_feats with a linear layer. So I want to ask that if I want to implement an attention model where the lstm takes fc_feats as input at step 0, and takes start token as input at step 1, like the figure below, then how to init the hidden states of lstm?
The text was updated successfully, but these errors were encountered: