Repository navigation
feat(objects): find objects with anytopdf, without ONNX Runtime in Lens - #228
Merged
Merged
Conversation
video.object_engine = anytopdf runs Lens's YOLOX model through anytopdf's objects plugin (anytopdf.analyze, sandboxed with no network). Components fetch anytopdf and the model for the objects step, not ONNX Runtime. The default stays yolox. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017tSHQyVLSbfTQvLeoPeMmW
…-272b8m # Conflicts: # CHANGELOG.md # fastapi_backend/app/domain/components.py
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Requested by Adeel · project thread
Before: finding objects with YOLOX needed ONNX Runtime installed in Lens's Python, which is heavy on a lean server or a Raspberry Pi.
After: Settings › Video › Object detector has a new choice, "YOLOX run by anytopdf". It runs the same YOLOX model through anytopdf's objects plugin, sandboxed with no network, so Lens needs no ONNX Runtime. The default stays YOLOX on ONNX Runtime.
How:
objects.AnytopdfObjectscallsanytopdf.analyze(cfg, picture, {"ANYTOPDF_OBJECTS_MODEL": yolox model})from #221, keeps the objects at or abovevideo.object_min_scoreand drops the faces. Components fetch anytopdf and YOLOX-s for the objects step when this engine is picked, and skip ONNX Runtime. The settings check, the Settings select, docs and changelog take the new value. anytopdf 0.4.0 was tested to find the same bus and four people with Lens'syolox_s.onnx.🤖 Generated with Claude Code
https://claude.ai/code/session_017tSHQyVLSbfTQvLeoPeMmW
Generated by Claude Code