py38

Signed-off-by: Wenqi Li <wenqil@nvidia.com>

Author: wyli

monai/metrics/utils.py

@@ -12,7 +12,7 @@
 from __future__ import annotations
 
 import warnings
-from functools import cache
+from functools import lru_cache
 from typing import Any, Sequence
 
 import numpy as np
@@ -374,7 +374,7 @@ def prepare_spacing(
 ENCODING_KERNEL = {2: [[8, 4], [2, 1]], 3: [[[128, 64], [32, 16]], [[8, 4], [2, 1]]]}
 
 
-@cache
+@lru_cache(maxsize=None)
 def _get_neighbour_code_to_normals_table(device=None):
     """
     returns a lookup table. For every binary neighbour code (2x2x2 neighbourhood = 8 neighbours = 8 bits = 256 codes)
@@ -657,14 +657,13 @@ def create_table_neighbour_code_to_surface_area(spacing_mm, device=None):
 
     Args:
         spacing_mm: a sequence of 3 numbers. Voxel spacing along the first 3 spatial axes.
-        deivce: device to put the table on.
+        device: device to put the table on.
 
     Returns:
         An array of size 256, mapping neighbourhood code to the surface area.
         ENCODING_KERNEL[3] which is the kernel used to compute the neighbourhood code.
     """
-    # compute the area for all 256 possible surface elements given a 2x2x2 neighbourhood) according to the spacing_mm
-    neighbour_code_to_surface_area = np.zeros([256])
+    # compute the area for all 256 possible surface elements given a 2x2x2 neighbourhood according to the spacing_mm
     c = _get_neighbour_code_to_normals_table(device)
     s = torch.as_tensor(
         [[[spacing_mm[1] * spacing_mm[2], spacing_mm[0] * spacing_mm[2], spacing_mm[0] * spacing_mm[1]]]],