-
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
Joeys2t adaptation #2
Conversation
get basic model
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.
Thank you for creating a PR.
a few things to get started:
- all code in a python project must be under a "package". in this case, the package is
signwriting_transcription
and so code should be under there (create as many subdirectories as you wish). Also, to allow for more approaches in the future, it might be wise to put the code undersignwriting_transcription/pose_to_text
for example (and then another could bevq_to_text
orvideo_to_text
etc) - It is important to create a README to explain your approach, or at least usage of it. If you want your
ipynb
file to be the instructions for now that is fine, but then use%%capture
to capture unnecessary outputs likepip install
orunzip
etc - I see you did not modify the
pyproject.toml
, but you should specify your dependencies (at leastjoeynmt
)
data_preparation/config.py
Outdated
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.
I think this config.py
should be config.yaml
since it only writes a yaml file.
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.
it is an easier way to use the config in the colab, is it ok?
training/evaluation.py
Outdated
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.
Instead of this file, you can implement sign-language-processing/signwriting-evaluation#1
and then use it like from signwriting_evaluation.metrics.similarity import SignWritingSimilarityMetric
for example
No description provided.