data pipeline for randomized initial goal + minimal files in data_collection#42
Open
data pipeline for randomized initial goal + minimal files in data_collection#42
Conversation
added 10 commits
November 7, 2025 20:43
This was referenced Nov 15, 2025
…an run 5), 40 test remaining
UttuG
changed the title
Collaborator
Author
|
Now has updated code for randomized initial pose too! Tested with both 4 & 5 parallel envs for 40 demonstrations and the run time is varying between 50-90 mins with 70 min being the average roughly memory usage is also more stable now, with 5 parallel envs stable now (didn't see much time improvement from 4 due to increased time in other parts of the pipeline due to increase) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
-Verified the run with sample 40 envs generated for demo_video
-Also integrates task verifier using object COM for distance calculation to goal pose (for both grasp trial and traj collection)
-sim_base as been retained as there are certain edits to it based on the data handling changes i made to the original sim_manip
-using sys path rather than relative import as internal (nested) imports were erroring out
Remaining:
Pipeline optimization (both memory + speed)
random initial pose