Add PAI-Bench-C reproduction guide for Cosmos3#224
Open
trungtpham wants to merge 1 commit into
Open
Conversation
trungtpham
force-pushed
the
features/paibenchc-reproduce
branch
14 times, most recently
from
80a3c53 to
4981e86
Compare
qianlim
reviewed
Jun 22, 2026
trungtpham
force-pushed
the
features/paibenchc-reproduce
branch
4 times, most recently
from
b0233cc to
f86e7ff
Compare
Collaborator
Author
|
Paibench-c results on demo 4 samples run by @trungtpham |
Collaborator
Author
|
@lfengad please help review this PR? Thanks |
trungtpham
force-pushed
the
features/paibenchc-reproduce
branch
from
f86e7ff to
cf2e416
Compare
|
QA evaluation report can be found at https://docs.google.com/document/d/1B6YkXoz9jnh4CBZqCuptLegHhqkorpa8BTQfKVkoP7w/edit?tab=t.ridcxjs8xsjg |
trungtpham
force-pushed
the
features/paibenchc-reproduce
branch
from
cf2e416 to
5e923a2
Compare
qmiao-hub
approved these changes
Jun 27, 2026
trungtpham
force-pushed
the
features/paibenchc-reproduce
branch
2 times, most recently
from
4b736b2 to
65585b7
Compare
- Add run_paibench_c.sh: robust self-contained script for PAI-Bench-C
generation + evaluation (edge/blur/depth/seg modalities)
- Venvs placed in TMPDIR to avoid Lustre stale file handle errors
- Auto-fix opencv-contrib-python → headless on GPU nodes (no libxcb)
- Health checks for torch, cv2, transformers, sam2 before torchrun
- Removed unnecessary groundingdino CUDA compilation (uses HF transformers)
- subshells instead of pushd/popd for safe directory changes
- Pre-eval video existence checks; clear diagnostics on failure
- Add assets/tasks.json: source of truth for per-task generation params,
prompts, UUIDs, and control signal paths (replaces prompts.json)
- Add specs/{edge,blur,depth,seg}.json: per-modality generation specs
- Add cookbook control signal preview videos (blur/depth/edge/seg/wsm)
trungtpham
force-pushed
the
features/paibenchc-reproduce
branch
from
65585b7 to
71cb8b9
Compare
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
4 participants
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.
Adds an end-to-end recipe for reproducing PAI-Bench Conditional Generation (PAI-Bench-C) results with Cosmos3 using the native Cosmos Framework PyTorch entrypoint.
New files under evaluation/cosmos3/generator/paibench_c/:
PAIBench-C Reproducibility
