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.

Sign up for GitHub

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

Jump to bottom

Documentation Notes #7

Open

3 tasks

JLenzy opened this issue Nov 3, 2022 · 1 comment

Collaborator

JLenzy commented Nov 3, 2022 •

edited

Loading

Possible to have a --requirements.txt file?
(3.1) minor correction, on my system I had to go up 2 directories to get it to work:

gmd_pickle_path="../../data/gmd/resources/storedDicts/groove_2bar-midionly.bz2pickle"))

3.1.3 I was slightly confused by the 'max_len' argument; wasn't sure if this was somehow related to batch size or the sequence length itself. Maybe clarifying this + adding a brief comment about the padding/slicing it does if len != maxlen

Will update this as I go along..

Collaborator Author

JLenzy commented Nov 18, 2022

Section 2: Models

Question on embedding size: Once this has been set, does it remain the same despite the size of the input vector? I am thinking in regards to NLP, where one sentence might be 6 words, and the next could be 13. If embed_size = 32 for example, would this stay static throughout any type of inference length? Does it need to be larger than the largest possible input matrix?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment