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.

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

fix scan modality #119

Merged
merged 1 commit into from
Nov 30, 2023
Merged

fix scan modality #119

merged 1 commit into from
Nov 30, 2023

Conversation

cremebrule
Copy link
Member

Fix scan modality to (a) not crash, and (b) be flexibly compatible with multiple channels

@cremebrule cremebrule requested a review from amandlek November 30, 2023 00:13
amandlek
amandlek reviewed Nov 30, 2023
View reviewed changes
Copy link
Member

@amandlek amandlek left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM in general! I'm wondering how we missed this before - I thought the MOMART experiments used the "scan" modality with the 1D conv and we tried reproducing results before merging that PR. I left one minor comment as well, and can approve the PR after that's resolved.

@cremebrule
Copy link
Member Author

LGTM in general! I'm wondering how we missed this before - I thought the MOMART experiments used the "scan" modality with the 1D conv and we tried reproducing results before merging that PR. I left one minor comment as well, and can approve the PR after that's resolved.

Yeah, I'm not sure how either. I know for MOMART I hardcoded the number of input channels to be 1, but there's no reason why that should be the case (e.g.: a 16-channel LIDAR vs. 1-channel).

In terms of things breaking, yeah I'm not entirely sure what changed -- my initial guess is that perhaps the torch implementation changed slightly, resulting in a different interface? very strange though

@amandlek amandlek merged commit b5ce962 into master Nov 30, 2023
@amandlek amandlek deleted the fix/scan-modality branch November 30, 2023 15:40
Dhanushvarma added a commit to Dhanushvarma/robomimic_vd that referenced this pull request Dec 13, 2023
@Dhanushvarma
Merge pull request #1 from ARISE-Initiative/master
7df309c 
fix scan modality (ARISE-Initiative#119)
Eubooks3003 pushed a commit to Eubooks3003/robomimic that referenced this pull request Oct 7, 2024
@cremebrule
fix scan modality (ARISE-Initiative#119)
3742eaa
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@amandlek amandlek amandlek approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@cremebrule @amandlek