-
Notifications
You must be signed in to change notification settings - Fork 6
[RSDK-10599] Add full keras support to tf-cpu #18
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
penguinland
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.
LPlausibleTM! but I defer to Khari, who knows this way better than I do.
3f397c5 to
7718c80
Compare
penguinland
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.
This still looks good to me, but I still defer to Khari's expertise
bhaney
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.
Some changes, mostly about defining the input and output tensors. Also:
- have you tested this on windows?
- release an -rc version from this branch, and find a .keras file from here and try it out to see it it loads properly. https://www.kaggle.com/models?framework=keras
- using the python SDK, create a random input and see if the infer works as intended
361786c to
fbf770c
Compare
|
Will close this for now as we revisit Keras support for the version of tf that is used in training |
Initial PR, just need eyes on it for now, still have to test on app.viam.com
Main logic in commit titled "logic changes for keras support"