-
Notifications
You must be signed in to change notification settings - Fork 2k
Add tensorflow.js export example #2190
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
Conversation
…ntributing and update changelog
docs/guide/export.rst
Outdated
| ------------------------------------ | ||
|
|
||
| See https://onnxruntime.ai/docs/tutorials/web/build-web-app.html | ||
| Full example code: https://github.com/JonathanColetti/CarDodgingGym and demo: https://jonathancoletti.github.io/CarDodgingGym/ |
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.
Please keep the link to the official doc too
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.
and cool demo =)
docs/guide/export.rst
Outdated
|
|
||
| The following is a simple example that showcases the full conversion + inference | ||
|
|
||
| .. code-block:: python |
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.
maybe just refer to the code above and say that the opset need to be changed
|
@araffin thanks for the input. I made the changes! let me know if anything is wrong or I misinterpreted something |
contributing.md setup more robust
araffin
left a comment
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, thanks =)
Description
closes #2189
I added detailed documentation for setup and inference in tensorflow.js along with clear explanations on each design choice
I added versioning pinning in the ONNX for better reproduceability along with an extra comment stating you can renormalize or unnormalize
I added an example project of mine in the export to ONNX-JS documentation. I can remove if unneeded but I thought it would add depth with a real world example
The command in
pip install -e .[docs,tests,extra]fails on zsh due tozsh: no matches found: .[docs,tests,extra]thus it was changed topip install -e '.[docs,tests,extra]'Motivation and Context
Types of changes
Checklist
make format(required)make check-codestyleandmake lint(required)make pytestandmake typeboth pass. (required)make doc(required)Note: You can run most of the checks using
make commit-checks.Note: we are using a maximum length of 127 characters per line