torch-geopooling 1.1.1__cp39-cp39-macosx_11_0_arm64.whl → 1.1.2__cp39-cp39-macosx_11_0_arm64.whl

torch_geopooling/__init__.py

@@ -1,3 +1,3 @@
 from typing import Final
 
-__version__: Final[str] = "1.1.1"
+__version__: Final[str] = "1.1.2"

torch_geopooling/functional/embedding.py

@@ -32,22 +32,26 @@ class Function(autograd.Function):
         weight: Tensor,
         padding: Tuple[int, int],
         exterior: ExteriorTuple,
+        reflection: bool,
     ) -> Tensor:
-        return _C.embedding2d(input, weight, padding, exterior)
+        return _C.embedding2d(input, weight, padding, exterior, reflection)
 
     @staticmethod
     def setup_context(ctx: FunctionCtx, inputs: Tuple, outputs: Tuple) -> None:
-        input, weight, padding, exterior = inputs
+        input, weight, padding, exterior, reflection = inputs
 
         ctx.save_for_backward(input, weight)
         ctx.padding = padding
         ctx.exterior = exterior
+        ctx.reflection = reflection
 
     @staticmethod
     def backward(ctx: FunctionCtx, grad: Tensor) -> Tuple[Optional[Tensor], ...]:
         input, weight = ctx.saved_tensors
-        grad_weight = _C.embedding2d_backward(grad, input, weight, ctx.padding, ctx.exterior)
-        return None, grad_weight, None, None
+        grad_weight = _C.embedding2d_backward(
+            grad, input, weight, ctx.padding, ctx.exterior, ctx.reflection
+        )
+        return None, grad_weight, None, None, None
 
 
 def embedding2d(
@@ -56,6 +60,7 @@ def embedding2d(
     *,
     padding: Tuple[int, int] = (0, 0),
     exterior: ExteriorTuple,
+    reflection: bool = True,
 ) -> Tensor:
     """
     Retrieves spatial embeddings from a fixed-size lookup table based on 2D coordinates.
@@ -77,9 +82,11 @@ def embedding2d(
         exterior: The geometric boundary of the learning space, specified as a tuple (X, Y, W, H),
             where X and Y represent the origin, and W and H represent the width and height of the
             space, respectively.
+        reflection: When true, kernel is wrapped around the exterior space, otherwise kernel is
+            squeezed into borders.
 
     Returns:
         Tensor: The retrieved spatial embeddings corresponding to the input coordinates.
     """
 
-    return Function.apply(input, weight, padding, exterior)
+    return Function.apply(input, weight, padding, exterior, reflection)

torch_geopooling/functional/embedding_test.py

@@ -26,6 +26,7 @@ def test_embedding2d() -> None:
         weight,
         padding=(3, 2),
         exterior=(-10.0, -10.0, 20.0, 20.0),
+        reflection=True,
     )
 
     assert result.size() == torch.Size([100, 7, 5, 3])

torch_geopooling/nn/embedding.py

@@ -46,6 +46,8 @@ class Embedding2d(nn.Module):
         exterior: The geometric boundary of the learning space, specified as a tuple (X, Y, W, H),
             where X and Y represent the origin, and W and H represent the width and height of the
             space, respectively.
+        reflection: When true, kernel is wrapped around the exterior space, otherwise kernel is
+            squeezed into borders.
 
     Shape:
         - Input: :math:`(*, 2)`, where 2 comprises x and y coordinates.
@@ -74,17 +76,27 @@ class Embedding2d(nn.Module):
         manifold: Tuple[int, int, int],
         exterior: _Exterior,
         padding: Tuple[int, int] = (0, 0),
+        reflection: bool = True,
     ) -> None:
         super().__init__()
         self.manifold = manifold
         self.exterior = cast(ExteriorTuple, tuple(map(float, exterior)))
         self.padding = padding
+        self.reflection = reflection
 
         self.weight = nn.Parameter(torch.empty(manifold, dtype=torch.float64))
         nn.init.zeros_(self.weight)
 
     def extra_repr(self) -> str:
-        return "{manifold}, exterior={exterior}, padding={padding}".format(**self.__dict__)
+        return "{manifold}, exterior={exterior}, padding={padding}, reflection={reflection}".format(
+            **self.__dict__
+        )
 
     def forward(self, input: Tensor) -> Tensor:
-        return F.embedding2d(input, self.weight, exterior=self.exterior, padding=self.padding)
+        return F.embedding2d(
+            input,
+            self.weight,
+            exterior=self.exterior,
+            padding=self.padding,
+            reflection=self.reflection,
+        )

{torch_geopooling-1.1.1.dist-info → torch_geopooling-1.1.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: torch-geopooling
-Version: 1.1.1
+Version: 1.1.2
 Summary: The geospatial pooling modules for neural networks in PyTorch
 Author-email: Yakau Bubnou <girokompass@gmail.com>
 License: GNU GENERAL PUBLIC LICENSE

{torch_geopooling-1.1.1.dist-info → torch_geopooling-1.1.2.dist-info}/RECORD

@@ -1,5 +1,5 @@
-torch_geopooling/_C.cpython-39-darwin.so,sha256=6d0f16d44-0X5D_g_WCXDy15xVQhM8OymZ2diDiOJs8,562520
-torch_geopooling/__init__.py,sha256=gocbEzjrMP-BkhotjSAi8QMuhKTEaRaMwBD6JC2R9is,60
+torch_geopooling/_C.cpython-39-darwin.so,sha256=5zgVSQT534Amq9WREdDbYUTOoSA4eoZc4R1cLKX5-T8,562584
+torch_geopooling/__init__.py,sha256=W3RCgJbj6HbE-qg2_ltJFtMf9KboKmOCMEZfS4eEQOI,60
 torch_geopooling/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 torch_geopooling/return_types.py,sha256=QhIKf_qxpppzuZzUrT-VacfbvZ6zKmSRu-WZOqL8wuE,898
 torch_geopooling/tiling.py,sha256=f1g0Gf__5zIOafZzDkwO62t9OqMDMBEYVtM2HXB5X0Y,2553
@@ -7,18 +7,18 @@ torch_geopooling/transforms.py,sha256=NHPBgx1L4-1745xNO_PvLuvbMH6DWi2rs1ViuRyBQA
 torch_geopooling/transforms_test.py,sha256=Cqp4VVObBVrc8HQ7uxkpe1EsQ5NxXrCI77BiUqngLXw,1196
 torch_geopooling/__bind__/python_module.cc,sha256=LLI363riung_4LI5ugN7Pm93iuoHDRF7n4Y4RlkzLYk,675
 torch_geopooling/functional/__init__.py,sha256=BCcS22yPWITm37M-EPD-PK6WrS7grikDR8uZdoO8sZ4,118
-torch_geopooling/functional/embedding.py,sha256=ER0KB-G7SoCsWJuNEqXRC_XcLdhqaCpn5OJPpUF9pLc,3337
-torch_geopooling/functional/embedding_test.py,sha256=B5a1MP0rynX01a1RmmTJHZxMi4Y68cQoblw-kQawHJM,1094
+torch_geopooling/functional/embedding.py,sha256=Pd01LuVhrDVRb35_7YaJwmdPeCYSZ1fzvvV7NZ03BR8,3639
+torch_geopooling/functional/embedding_test.py,sha256=n844pekbw01I1WtAMsRfvlw4nFSBTrPNjMtRrUPd1ZY,1119
 torch_geopooling/functional/pooling.py,sha256=MuJfPW_RC4slgzWBO2ngQIBTzlZXeW7DBqV3ooIOSw4,12060
 torch_geopooling/functional/pooling_test.py,sha256=qBT_WVbwyANolwg7-rE7KimF-bAEDB44guBl4OQuQhE,3005
 torch_geopooling/nn/__init__.py,sha256=fWrhfQu0_KzW7VUesk31Sy3n3Om2c5g5dGA3vrLcCg4,102
-torch_geopooling/nn/embedding.py,sha256=3uF0zbtql90FUpRNKJK_oUcdL8_J6mrOpPm-zTJWlX4,3350
+torch_geopooling/nn/embedding.py,sha256=MD8oTH2IP2g368NVZJoxcXqND-pQ1gXDMvt9F31rMbk,3697
 torch_geopooling/nn/embedding_test.py,sha256=msUeidL9Xkf3AKCPGQH9SJAhfkS7dyqYRzsH88Pt1uY,1505
 torch_geopooling/nn/pooling.py,sha256=_NnGB45dWTZy4MQokFfmJL3as-EPVU3liwOuAmWbv1Y,14219
 torch_geopooling/nn/pooling_test.py,sha256=AqnkpaQ6LcQxh5bWkuDuBAJ2XiBc-C2zVuUp5hynzBM,4794
-torch_geopooling-1.1.1.dist-info/LICENSE,sha256=jLc4eyvG8hqxH4AdKAjK2DwXoP68qjHiGfq8eP5ubBI,35069
-torch_geopooling-1.1.1.dist-info/METADATA,sha256=20wqd_pqv0QO2bIkgG078qmqt3DXXy2Uxk1xrKIKpp8,44675
-torch_geopooling-1.1.1.dist-info/WHEEL,sha256=_exXVVrX7A7i2-EOwk1kG5BcIkGQg9kfHel4XXV7Pbs,108
-torch_geopooling-1.1.1.dist-info/dependency_links.txt,sha256=JqLDcYHtEaQB51V72n3gAJvRd36bpoPk9qgTbot-Lx4,37
-torch_geopooling-1.1.1.dist-info/top_level.txt,sha256=3geTL2nsLvybdtr1psWIE6h63B1LuyIIyWWv0rDafTk,17
-torch_geopooling-1.1.1.dist-info/RECORD,,
+torch_geopooling-1.1.2.dist-info/LICENSE,sha256=jLc4eyvG8hqxH4AdKAjK2DwXoP68qjHiGfq8eP5ubBI,35069
+torch_geopooling-1.1.2.dist-info/METADATA,sha256=XkmsKm7tWfdkK4HOKA8fwh04XcbkkjbIgzmXQA2JVAE,44675
+torch_geopooling-1.1.2.dist-info/WHEEL,sha256=_exXVVrX7A7i2-EOwk1kG5BcIkGQg9kfHel4XXV7Pbs,108
+torch_geopooling-1.1.2.dist-info/dependency_links.txt,sha256=JqLDcYHtEaQB51V72n3gAJvRd36bpoPk9qgTbot-Lx4,37
+torch_geopooling-1.1.2.dist-info/top_level.txt,sha256=3geTL2nsLvybdtr1psWIE6h63B1LuyIIyWWv0rDafTk,17
+torch_geopooling-1.1.2.dist-info/RECORD,,