π Geometric Computer Vision Library for Spatial AI
Python artificial-intelligencecomputer-visiondeep-learninghacktoberfestimage-processingmachine-learningneural-networkpythonpytorchroboticsspatial-ai
fix(enhance): build the CLAHE slow-path bin centres and bandwidth in the promoted tile dtype (#6383)
Prateekshit Jaiswal37afdb3c4df9
diff --git a/changelog.d/6383.fixed.md b/changelog.d/6383.fixed.mdnew file mode 100644index 000000000..d26b623b9--- /dev/null+++ b/changelog.d/6383.fixed.md@@ -0,0 +1 @@+`equalize_clahe(..., slow_and_differentiable=True)` builds its soft-histogram bin centres and bandwidth in float64 for a float64 image and in float32 for every other dtype. In 0.9.0 they were built in the default dtype: a float64 image was equalized with float32 centres, up to about 7e-5 relative away from a float64 computation, and a float64 default dtype changed the result for every input dtype, by up to 3e-2 for a bfloat16 image. The fast path is unchanged, and float32, float16 and bfloat16 results under the float32 default are bit-identical to 0.9.0.diff --git a/kornia/enhance/equalization.py b/kornia/enhance/equalization.pyindex ee6522c56..5f367dc75 100644--- a/kornia/enhance/equalization.py+++ b/kornia/enhance/equalization.py@@ -239,9 +239,12 @@ def _compute_luts(# In float16 the clipped total of a 256 x 256 tile overflows to inf, and bfloat16 rounds counts above 256.histos = _tiles_histc(tiles, num_bins)else:- bins: torch.Tensor = torch.linspace(0, 1, num_bins, device=tiles.device)+ # The centres and bandwidth follow float64 tiles; every other dtype stays float32 because histogram+ # evaluates half-precision kernels in float32.+ centre_dtype = torch.promote_types(tiles.dtype, torch.float32)+ bins: torch.Tensor = torch.linspace(0, 1, num_bins, device=tiles.device, dtype=centre_dtype)# histogram already returns (T, num_bins); squeeze() dropped the tile axis for a single tile- histos = histogram(tiles, bins, torch.tensor(0.001))+ histos = histogram(tiles, bins, torch.tensor(0.001, dtype=centre_dtype))histos *= pixelsif isinstance(clip, torch.Tensor):diff --git a/tests/enhance/test_equalization.py b/tests/enhance/test_equalization.pyindex 5b56921fb..00a4d8abd 100644--- a/tests/enhance/test_equalization.py+++ b/tests/enhance/test_equalization.py@@ -677,6 +677,43 @@ class TestEqualization(BaseTester):flipped = enhance.equalize_clahe(img.flip(dim), 2.0, (3, 3), slow_and_differentiable)self.assert_close(flipped, out.flip(dim))+ def test_clahe_slow_path_does_not_depend_on_the_default_dtype_6366(self, device, dtype):+ # Differentiable CLAHE takes its bin centres and 0.001 bandwidth from the tile dtype, so+ # torch.set_default_dtype(torch.float64) must not change the output (#6366). The image is the+ # 2x3x32x40 seed-10 case from that report, cast to the parametrized dtype.+ if device.type == "mps":+ pytest.skip("MPS has no float64")+ x = torch.rand(2, 3, 32, 40, generator=torch.Generator().manual_seed(10), dtype=torch.float64).to(device, dtype)+ out = enhance.equalize_clahe(x, slow_and_differentiable=True)+ previous = torch.get_default_dtype()+ torch.set_default_dtype(torch.float64)+ try:+ expected = enhance.equalize_clahe(x, slow_and_differentiable=True)+ finally:+ torch.set_default_dtype(previous)+ self.assert_close(out, expected, rtol=0, atol=0)++ def test_clahe_slow_path_centres_in_promoted_tile_dtype_6366(self, device, dtype, monkeypatch):+ # Float64 tiles get float64 centres and bandwidth; every other dtype keeps the float32 ones it had, so its+ # output is unchanged (#6366). The test above cannot see a dtype that ignores the default dtype but is wrong.+ from kornia.enhance import equalization++ calls = []+ histogram = equalization.histogram++ def spy(x, bins, bandwidth, *args, **kwargs):+ calls.append((bins, bandwidth))+ return histogram(x, bins, bandwidth, *args, **kwargs)++ monkeypatch.setattr(equalization, "histogram", spy)+ img = torch.linspace(0, 1, 256, device=device, dtype=dtype).view(1, 1, 16, 16)+ enhance.equalize_clahe(img, slow_and_differentiable=True)+ expected = torch.promote_types(dtype, torch.float32)+ ((bins, bandwidth),) = calls+ assert bins.dtype == expected+ assert bandwidth.dtype == expected+ self.assert_close(bins, torch.linspace(0, 1, 256, device=device, dtype=expected), rtol=0, atol=0)+def test_clahe_odd_tiles_gradcheck_5812(self, device):torch.manual_seed(4)img = torch.rand(1, 1, 9, 15, device=device, dtype=torch.float64)