Conversation
Major Features: - Add SAM3-Image v2 (3 ONNX) with integrated geometry encoder - Implement few-images+many-prompts optimized pipeline - Add frame skipping support for video processing - Add infinity progress bar support Performance Optimizations: - Optimize text_cache to be backend-agnostic (CPU/CUDA/TensorRT) - Minimize device-to-CPU transfers and type conversions - Reduce decoder call count from images*prompts to prompts - Refactor postprocess to use zero-copy views Code Quality: - Remove TODO comments and cleanup pipeline code - Format Python inference scripts with proper line breaks - Collapse v1 content in README for better organization - Update documentation links and examples New Files: - scripts/sam3-image/export_v2.py: ONNX export for v2 models - scripts/sam3-image/inference_v2.py: Inference script for v2 models - src/processor/image/cuda/kernels/: CUDA kernel implementations - tests/: Test suite additions Breaking Changes: - Update default batch sizes and configurations - Modify progress bar to support infinity display - Update dataloader to support frame skipping
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Major Features:
SAM3-Image v2(3 ONNX) with integrated geometry encoder.YOLOE-26 (prompt-based)model and updatedYOLOE-26 (prompt-free, one-to-one)variantframe-skippingsupport forwebcaminputLetterboxon both CPU and CUDA, addressing performance issues with YOLOE-26 models