Skip to content
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

DocumentLSTMEmbeddings use GRU instead of LSTM #511

Closed
kubapok opened this issue Feb 16, 2019 · 1 comment
Closed

DocumentLSTMEmbeddings use GRU instead of LSTM #511

kubapok opened this issue Feb 16, 2019 · 1 comment
Labels
bug Something isn't working

Comments

@kubapok
Copy link
Contributor

kubapok commented Feb 16, 2019

In DocumentLSTMEmbeddings there is:

self.rnn = torch.nn.GRU(self.embeddings_dimension, hidden_size, num_layers=rnn_layers, bidirectional=self.bidirectional)

which is inconsistent naming. Both GRU and LSTM are type of RNN networks, but GRU is not the same as LSTM.

@kubapok kubapok added the bug Something isn't working label Feb 16, 2019
kubapok added a commit to kubapok/flair that referenced this issue Feb 16, 2019
alanakbik pushed a commit that referenced this issue Feb 19, 2019
GH-511: change DocumentLSTMEmbeddings to use LSTM instead of GRU
@alanakbik
Copy link
Collaborator

fixed in #512 - thanks!!

stefan-it pushed a commit that referenced this issue Feb 19, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

2 participants