fix(yolo pipeline): handle 5D batch tensors in graph stream queues#742
Merged
fix(yolo pipeline): handle 5D batch tensors in graph stream queues#742
Conversation
In Perform Mode, preprocessor outputs like vace_input_frames and vace_input_masks bypass stream queues and are passed as raw [B,C,F,H,W] tensors via the parameter path. In Graph Mode (Workflow Builder), these ports have explicit stream edges, so the queue system tried to apply uint8 conversion and dim-0 frame splitting—which mangles 5D tensors. Convert 5D [B,C,F,H,W] tensors to [B*F,H,W,C] frame format before queuing, and add mask preprocessing in PreprocessVideoBlock so masks arriving as frame lists are properly assembled into [B,1,F,H,W] tensors. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> Signed-off-by: Rafal Leszko <[email protected]>
Contributor
🚀 fal.ai Preview Deployment
TestingConnect to this preview deployment by running this on your branch: 🧪 E2E tests will run automatically against this deployment. |
Contributor
❌ E2E Tests failed
Test ArtifactsCheck the workflow run for screenshots, traces, and failure details. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In Perform Mode, preprocessor outputs like vace_input_frames and vace_input_masks bypass stream queues and are passed as raw [B,C,F,H,W] tensors via the parameter path. In Graph Mode (Workflow Builder), these ports have explicit stream edges, so the queue system tried to apply uint8 conversion and dim-0 frame splitting—which mangles 5D tensors.
Convert 5D [B,C,F,H,W] tensors to [B*F,H,W,C] frame format before queuing, and add mask preprocessing in PreprocessVideoBlock so masks arriving as frame lists are properly assembled into [B,1,F,H,W] tensors.