Add fast slab lookup for the GeometryOracle, replacing knn as the default

miniCaloSim's detector is a stack of planar layer slabs along one axis, so
material/layer_id are a pure function of depth. The new "slab" method
exploits this with an exact O(log #segments) binary search over
depth-axis segment boundaries, instead of a nearest-neighbour search over
hundreds of thousands of reference points — much cheaper per call, which
matters since the oracle is queried on every autoregressive rollout step.
"knn"/"svm" remain as fallbacks for non-slab geometries.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
2026-07-08 11:42:12 +02:00
co-authored by Claude Sonnet 5
parent 436d9fa4d4
commit 3faa272562
5 changed files with 379 additions and 47 deletions
+93 -1
View File
@@ -26,7 +26,9 @@ def _build(subsample=30000, method="knn", escape_factor=5.0):
batches = [_box_batch(20000, rng) for _ in range(3)]
with patch.object(g, "_iter_point_batches", lambda p: iter(batches)):
return g.build_geometry_oracle(
[Path("x")], method=method, subsample=subsample,
[Path("x")],
method=method,
subsample=subsample,
escape_factor=escape_factor,
)
@@ -84,3 +86,93 @@ def test_svm_method_has_escape_tree():
assert orc._ref_tree is not None
_, _, escaped = orc.query(np.array([[1e5, 0.0, 0.0]]))
assert escaped[0]
def _layer_batch(n, rng):
"""Two 100mm slabs along z (with an air gap between/around them), bounded
to a 100x100mm transverse footprint — miniCaloSim's actual layer-stack
shape."""
z = rng.uniform(-20.0, 220.0, n).astype(np.float32)
x = rng.uniform(-50.0, 50.0, n).astype(np.float32)
y = rng.uniform(-50.0, 50.0, n).astype(np.float32)
material = np.full(n, "G4_AIR", dtype=object)
layer_id = np.full(n, -1, dtype=np.int64)
in_l0 = (z >= 0.0) & (z < 100.0)
in_l1 = (z >= 110.0) & (z < 210.0)
material[in_l0] = "G4_PbWO4"
layer_id[in_l0] = 0
material[in_l1] = "G4_W"
layer_id[in_l1] = 1
pos = np.stack([x, y, z], axis=1)
return pos, material, layer_id
def _build_slab(subsample=60000, n_bins=500, escape_factor=5.0):
rng = np.random.default_rng(0)
batches = [_layer_batch(20000, rng) for _ in range(3)]
with patch.object(g, "_iter_point_batches", lambda p: iter(batches)):
return g.build_geometry_oracle(
[Path("x")],
method="slab",
subsample=subsample,
escape_factor=escape_factor,
depth_axis=2,
n_bins=n_bins,
)
def test_slab_is_default_method():
rng = np.random.default_rng(0)
batches = [_layer_batch(20000, rng)]
with patch.object(g, "_iter_point_batches", lambda p: iter(batches)):
orc = g.build_geometry_oracle([Path("x")], subsample=20000)
assert orc.metadata["method"] == "slab"
assert orc._slab is not None
def test_slab_classes_discovered():
orc = _build_slab()
assert set(orc.classes) == {("G4_PbWO4", 0), ("G4_W", 1), ("G4_AIR", -1)}
def test_slab_query_labels_by_depth():
orc = _build_slab()
pos = np.array(
[[0.0, 0.0, 50.0], [0.0, 0.0, 105.0], [0.0, 0.0, 150.0]]
) # layer 0, gap, layer 1
material, layer_id, escaped = orc.query(pos)
assert list(material) == ["G4_PbWO4", "G4_AIR", "G4_W"]
assert list(layer_id) == [0, -1, 1]
assert not escaped.any()
def test_slab_escape_beyond_depth_range():
orc = _build_slab()
pos = np.array([[0.0, 0.0, 50.0], [0.0, 0.0, 1e5]])
_, _, escaped = orc.query(pos)
assert not escaped[0]
assert escaped[1]
def test_slab_escape_beyond_transverse_radius():
orc = _build_slab()
pos = np.array([[0.0, 0.0, 50.0], [1e5, 1e5, 50.0]])
_, _, escaped = orc.query(pos)
assert not escaped[0]
assert escaped[1]
def test_slab_save_load_roundtrip(tmp_path):
orc = _build_slab()
p = tmp_path / "slab_oracle.pkl"
orc.save(p)
loaded = g.GeometryOracle.load(p)
pos = np.array(
[[0.0, 0.0, 50.0], [0.0, 0.0, 105.0], [0.0, 0.0, 150.0], [0.0, 0.0, 1e5]]
)
m0, l0, e0 = orc.query(pos)
m1, l1, e1 = loaded.query(pos)
assert (m0 == m1).all() and (l0 == l1).all() and (e0 == e1).all()
assert loaded.escape_threshold == orc.escape_threshold
assert loaded._slab is not None