Conversation
…er inference - detect.py: auto-export .pt → .mlpackage when device=mps, cached for reuse - deploy.sh: pre-convert default nano model to CoreML during installation - requirements_mps.txt: added coremltools>=8.0 - config.yaml: added use_coreml toggle (default: true) - Falls back to PyTorch MPS if CoreML export or loading fails
…te stats PerfTracker instruments every pipeline stage: - file_read: frame path check - inference: model prediction - postprocess: bbox extraction + class filtering - emit: JSON serialization Emits perf_stats event every 50 frames with avg/min/max/p50/p95/p99. Also tracks one-time model_load_ms and coreml_export_ms.
…kend inference New shared library at skills/lib/env_config.py: - HardwareEnv.detect(): auto-detect CUDA, ROCm, MPS, Intel, CPU - export_model(): auto-export to TensorRT/ONNX/CoreML/OpenVINO - load_optimized(): load cached model with PyTorch fallback detect.py: replaced inline CoreML logic with HardwareEnv (2 lines) deploy.sh: uses env_config for hardware detection + generalized pre-conversion New: requirements_intel.txt (OpenVINO) Updated: requirements_cuda (tensorrt), rocm (onnxruntime-rocm), cpu (onnxruntime)
…ardware acceleration SKILL.md v2.0: - Hardware acceleration section (TensorRT/CoreML/OpenVINO/ONNX) - env_config.py integration documentation - Auto start parameter documentation - Performance monitoring (perf_stats) documentation - Requirements files reference table - Updated protocol examples with backend/format/gpu fields README.md: - Updated yolo-detection-2026 description with acceleration formats - Added hardware environment layer to roadmap (completed) config.yaml: renamed use_coreml → use_optimized (all backends) detect.py: backward-compatible config key migration
…re accel, AI-driven skill integration
… add AI-assisted install + skill dev guide
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.
No description provided.