-
Notifications
You must be signed in to change notification settings - Fork 13
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
Incompatible shapes #25
Comments
Hello, thanks for your question. I would need more information and/or ability to replicate the error in order to help. It may simply be a versioning issue - perhaps the versions of libraries you have installed handle things differently and the code needs to be updated. Ideally, you can stand this up as either a Google Colab and/or a Kaggle kernel and share a link with us, so that we can replicate the error and take it from there. Just glancing at your output, it seems the code is expecting the second shape to be [74,128] not [73,128] |
Hi @azunre, thank you for the reply. For my local spec, I am running the notebook using Jupyter notebook installed via Conda on Macbook M1.
I also find this Kaggle link listed on the README, under Notebooks section for eng_twi_transformer.ipynb. Any help or advice would be greatly appreciated. |
Hi,
Thank you for building and sharing this translation system.
I am trying out the
eng_twi_transformer.ipynb
using jupyter notebook with the provided data, jw300.en and jw300.tw.Everything seems to work until I tried to execute the predict function (line 544).
Here are the results on the console:
I am not sure why this happens. Any help or advice is greatly appreciated.
Thank you.
The text was updated successfully, but these errors were encountered: