Skip to content
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

In colab, load tensorboard settings from the command line: %tensorboard --settings #6867

Open
g-i-o-r-g-i-o opened this issue Jun 12, 2024 · 3 comments

Comments

@g-i-o-r-g-i-o
Copy link

g-i-o-r-g-i-o commented Jun 12, 2024

Every time I start colab and tensorboard, I have to select the same settings, which is quite boring.
If possible, I'd like to ask to control the "settings", for example (scalars Smoothing = 0.99)

with this command
%tensorboard --logdir="{BOARD_PATH}"
--scalars-smoothing=0.99
--Ignore-outliers-in-chart-scaling=False

and maybe even:

select the (multple) data to be shown, on the base of the folder name? --run="Jun08_10-40-47"
toggle full size mode

$$Clipboard01

thanks

@JamesHollyer
Copy link
Contributor

This seems like a reasonable feature. However, we will probably not be able to find time to invest into it. We are however, saving settings such as smoothing in local storage. So if your domain is the same these settings should be saved.

@g-i-o-r-g-i-o
Copy link
Author

Thanks a lot for considering this, but in google colab, at each restart, the settings are lost.

@JamesHollyer
Copy link
Contributor

Ah yes, you are correct. Sorry for the inconvenience. I can see how that could get tedious. You are welcome to dig into the code and implement this for yourself. Depending on how involved the change would be we could potentially review it and submit it. I cannot promise we invest the time into reviewing the code if it is a big involved PR. I could see this being small and easy to review/approve though.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants