dtourolleandClaude Opus 5
f33403fff8
Closes both violations SPEC.md named under "Every model gets the input it was trained for". They are one bug, not two. The dense stream defaulted to 12 fps, so a 100-frame TransNetV2 window spanned ~8.3 s against the ~4 s it was trained on: half-speed motion over twice its temporal context. Boundary timestamps stayed correct throughout, which is exactly why the degradation was invisible and why the compressed separation it produced (~0.50 baseline against ~0.7+ peaks) was read as a property of the ONNX export rather than of the input. Dedup then merged boundaries closer than a literal 0.04 s — one frame at 25 fps, and wider than a frame at 30, so two cuts on consecutive frames became one. Nothing in scenes.json showed it; the file simply had fewer boundaries. Native rate is where that constant did the most damage, which is why fixing the decode rate without fixing the dedup would have made things worse. dedup_window_sec() now takes the median interval the detector was actually fed and halves it. Half a frame rather than a whole one: the only thing being merged is one frame scored by two overlapping windows, and two distinct frames are a full interval apart. Cost is real — dense decode is the pipeline's cost driver. It is accepted; dense_scale and scene_stride remain the reductions that do not run the model off-distribution. scene_threshold 0.60 was fitted against the 12 fps input and is now stale, so VR-006 goes from Low to Medium: it is no longer a refinement, it is a constant that no longer describes the input. AR-002 rides along because it was already implemented, just untagged and unverified — the register said Planned while the code was correct. The size filter becomes FaceDetectorFunc::drop_undersized(), tested at the threshold and at dense_scale 0.5, and checked end to end against the superhero dump, whose smallest face is exactly its recorded 32 px minimum, so the fixture check cannot pass vacuously. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> TRACES: AR-002, AR-011 | SR-002 | UT-002, UT-003, IT-001
72 lines
3.0 KiB
CMake
72 lines
3.0 KiB
CMake
# ── Unit tests ────────────────────────────────────────────────────────────────
|
|
# Pure, GPU-free, model-free tests. The similarity tests compile the GEMM backend
|
|
# directly with SAE_GEMM_CPU so the suite builds and runs on a machine without a
|
|
# GPU regardless of the main build's SAE_GEMM_BACKEND selection.
|
|
|
|
find_package(Catch2 3 QUIET)
|
|
if(NOT Catch2_FOUND)
|
|
include(FetchContent)
|
|
FetchContent_Declare(
|
|
Catch2
|
|
GIT_REPOSITORY https://github.com/catchorg/Catch2.git
|
|
GIT_TAG v3.5.3
|
|
)
|
|
FetchContent_MakeAvailable(Catch2)
|
|
endif()
|
|
|
|
add_executable(sae_tests
|
|
test_similarity.cpp
|
|
test_calibration.cpp
|
|
test_gallery_store.cpp
|
|
test_face_utils.cpp
|
|
test_track_gallery.cpp
|
|
test_face_tracker.cpp
|
|
test_track_registry.cpp
|
|
test_face_detector_node.cpp
|
|
test_scene_detector_node.cpp
|
|
test_replay_fixtures.cpp
|
|
test_audio_signature.cpp
|
|
${CMAKE_SOURCE_DIR}/src/backends/gemm_backend.cpp
|
|
${CMAKE_SOURCE_DIR}/src/gallery/gallery_store.cpp
|
|
${CMAKE_SOURCE_DIR}/src/audio_signature.cpp
|
|
${CMAKE_SOURCE_DIR}/src/gallery/embedder_stamp.cpp
|
|
)
|
|
target_include_directories(sae_tests PRIVATE ${CMAKE_SOURCE_DIR}/src)
|
|
# SAE_GEMM_CPU: build the CPU reference GEMM regardless of the main backend.
|
|
# SAE_MODELS_DIR: config.hpp (pulled in by track_gallery.hpp) bakes model paths.
|
|
# SAE_TEST_FIXTURES_DIR: the audio golden vector is read from the source tree,
|
|
# not copied, so the file the plugin repo shares is the file under test.
|
|
# AR-026/AR-027: exercise the same kernel CI actually runs. Without this the
|
|
# suite compiles the scalar fallback while the CPU builder image links OpenBLAS,
|
|
# so the tested path and the shipped path would differ.
|
|
find_package(PkgConfig QUIET)
|
|
if(PkgConfig_FOUND)
|
|
pkg_check_modules(OPENBLAS_T QUIET openblas)
|
|
endif()
|
|
if(OPENBLAS_T_FOUND)
|
|
target_include_directories(sae_tests PRIVATE ${OPENBLAS_T_INCLUDE_DIRS})
|
|
target_link_libraries(sae_tests PRIVATE ${OPENBLAS_T_LINK_LIBRARIES})
|
|
endif()
|
|
|
|
target_compile_definitions(sae_tests PRIVATE
|
|
$<$<BOOL:${OPENBLAS_T_FOUND}>:SAE_GEMM_CBLAS>
|
|
SAE_GEMM_CPU
|
|
SAE_MODELS_DIR="${SAE_MODELS_DIR}"
|
|
SAE_TEST_FIXTURES_DIR="${CMAKE_CURRENT_SOURCE_DIR}/fixtures")
|
|
# gallery_store.cpp + gallery_calibration.hpp use nlohmann/json and HDF5
|
|
# (galleries are HDF5-native, see src/gallery/gallery_store.cpp); face_utils.hpp
|
|
# and the calibration GEMM pull in OpenCV (calib3d/imgproc/core) via types.hpp.
|
|
# ffmpeg_libs: audio_signature.cpp decodes the golden fixture (avformat/avcodec/
|
|
# avutil/swresample). Still GPU-free — the audio path is pure CPU.
|
|
target_link_libraries(sae_tests PRIVATE
|
|
Catch2::Catch2WithMain
|
|
nlohmann_json::nlohmann_json
|
|
ffmpeg_libs
|
|
${OpenCV_LIBS}
|
|
${HDF5_CXX_LIBRARIES})
|
|
target_include_directories(sae_tests PRIVATE ${HDF5_INCLUDE_DIRS})
|
|
|
|
include(CTest)
|
|
include(Catch)
|
|
catch_discover_tests(sae_tests)
|