-
Notifications
You must be signed in to change notification settings - Fork 0
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
Rewrite training and inference code to more modern pytorch, add some functionalities and models #20
Conversation
annaproxy
commented
Jul 14, 2021
•
edited
Loading
edited
- Added pytorch dataset and dataloader instead of manual random sampler
- Use torch.optim instead of manual update
- Dataset now uses beginning of speech as well as end of speech tag
- Added nn.RNN instead of manual RNN
- Added embeddings (currently still one-hot, but could be made trainable) instead of manual one-hot
- Add comprehensive Dutch dictionary for pretraining
- Split notebook into two notebooks: one for training, one for inference
- CUDA can now be used for training and inference
- Add pre-trained Dutch model
…el (not the newer, 'cooler' one)
All code is used from modules
Co-authored-by: Sasafrass <36883067+Sasafrass@users.noreply.github.com>
… into anna-clean-notebook
Co-authored-by: Sasafrass <36883067+Sasafrass@users.noreply.github.com>
Co-authored-by: Sasafrass <36883067+Sasafrass@users.noreply.github.com>
Co-authored-by: Sasafrass <36883067+Sasafrass@users.noreply.github.com>
Added some formatting stuff in a review branch |
when running flask run
and generating a word, I get an error on this branch. Not sure if that is some db update stuff (tried running flask db update) or something in the code
Anna clean notebook review
…ocab object is there
Anything else? If no, can I merge? uwu |
Issue is addressed in latest hotfix. |
Nope, everything LGTM now! Happy merging! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM