feat(cnn_v3): Phase 5 complete — parity validation passing (36/36 tests)

- Add test_cnn_v3_parity.cc: zero_weights + random_weights tests
- Add gen_test_vectors.py: PyTorch reference implementation for enc0/enc1/bn/dec1/dec0
- Add test_vectors.h: generated C header with enc0, dec1, output expected values
- Fix declare_nodes(): intermediate textures at fractional resolutions (W/2, W/4)
  using new NodeRegistry::default_width()/default_height() getters
- Add layer-by-layer readback (enc0, dec1) for regression coverage
- Final parity: enc0 max_err=1.95e-3, dec1 max_err=1.95e-3, out max_err=4.88e-4

handoff(Claude): CNN v3 parity done. Next: train_cnn_v3.py (FiLM MLP training).

1 files changed, 18 insertions, 0 deletions

diff --git a/cmake/DemoTests.cmake b/cmake/DemoTests.cmake
index 0b7fbb7..69b9195 100644
--- a/cmake/DemoTests.cmake
+++ b/cmake/DemoTests.cmake
@@ -222,6 +222,24 @@ if(NOT DEMO_STRIP_ALL AND DEMO_WORKSPACE STREQUAL "main")
         STB_IMAGE_WRITE_IMPLEMENTATION)
 endif()
 
+# CNN v3 parity test (zero-weight + random-weight vs Python reference)
+if(NOT DEMO_STRIP_ALL AND DEMO_WORKSPACE STREQUAL "main")
+    add_demo_test(test_cnn_v3_parity CnnV3ParityTest gpu
+        src/tests/gpu/test_cnn_v3_parity.cc
+        src/tests/common/webgpu_test_fixture.cc
+        ${PLATFORM_SOURCES}
+        ${GEN_DEMO_CC})
+
+    target_include_directories(test_cnn_v3_parity PRIVATE
+        ${CMAKE_CURRENT_SOURCE_DIR}
+        ${CMAKE_CURRENT_SOURCE_DIR}/cnn_v3/src)
+
+    target_link_libraries(test_cnn_v3_parity PRIVATE
+        gpu util procedural ${DEMO_LIBS})
+
+    demo_add_asset_deps(test_cnn_v3_parity shaders)
+endif()
+
 # GPU Composite Texture Test (Phase 4)
 add_demo_test(test_gpu_composite GpuCompositeTest gpu
     src/tests/gpu/test_gpu_composite.cc