Math/AveragePooling

deeptrack/math.py

@@ -1069,24 +1069,23 @@ def __init__(
         super().__init__(ndimage.median_filter, size=ksize, **kwargs)
 
 
-#TODO ***AL*** revise Pool - torch, typing, docstring, unit test
-class Pool(Feature):
+class Pool(Feature): # Deprecated, children will be independent in the future.
     """Downsamples the image by applying a function to local regions of the
     image.
 
     This class reduces the resolution of an image by dividing it into
     non-overlapping blocks of size `ksize` and applying the specified pooling
     function to each block. The result is a downsampled image where each pixel
     value represents the result of the pooling function applied to the
-    corresponding block.
+    corresponding block. This pooling only works with numpy functions.  
 
     Parameters
     ----------
-    pooling_function: function
+    pooling_function:  Numpy function
         A function that is applied to each local region of the image.
         DOES NOT NEED TO BE WRAPPED IN ANOTHER FUNCTION.
-        The `pooling_function` must accept the input image as a keyword argument
-        named `input`, as it is called via `utils.safe_call`.
+        The `pooling_function` must accept the input image as a keyword
+        argument named `input`, as it is called via `utils.safe_call`.
         Examples include `np.mean`, `np.max`, `np.min`, etc.
     ksize: int
         Size of the pooling kernel.
@@ -1095,7 +1094,8 @@ class Pool(Feature):
 
     Methods
     -------
-    `get(image: np.ndarray | Image, ksize: int, **kwargs: Any) --> np.ndarray`
+    `get(image: NDArray,
+         ksize: int, **kwargs: Any) --> NDArray`
         Applies the pooling function to the input image.
 
     Examples
@@ -1152,17 +1152,17 @@ def __init__(
 
     def get(
         self: Pool,
-        image: np.ndarray | Image,
+        image: NDArray,
         ksize: int,
         **kwargs: Any,
-    ) -> np.ndarray:
+    ) -> NDArray:
         """Applies the pooling function to the input image.
 
-        This method applies the pooling function to the input image.
+        This method applies `pooling_function` to the input image.
 
         Parameters
         ----------
-        image: np.ndarray
+        image: NDArray | torch.Tensor
             The input image to pool.
         ksize: int
             Size of the pooling kernel.
@@ -1171,7 +1171,7 @@ def get(
 
         Returns
         -------
-        np.ndarray
+        NDArray | torch.Tensor
             The pooled image.
 
         """
@@ -1188,15 +1188,20 @@ def get(
         )
 
 
-#TODO ***AL*** revise AveragePooling - torch, typing, docstring, unit test
 class AveragePooling(Pool):
     """Apply average pooling to an image.
 
-    This class reduces the resolution of an image by dividing it into
-    non-overlapping blocks of size `ksize` and applying the average function to
-    each block. The result is a downsampled image where each pixel value
-    represents the average value within the corresponding block of the
-    original image.
+    This class inherits from `Pool` to reduce the resolution of an image by
+    dividing it into non-overlapping blocks of size `ksize` and applying the
+    `max` function to each block. The result is a downsampled image where each
+    pixel value represents the maximum value within the corresponding block of
+    the original image. This is useful for reducing the size of an image while
+    retaining the most significant features.
+
+    If the backend is numpy, the downsampling is performed using
+    `skimage.measure.block_reduce`.
+    If the backend is torch, the downsampling
+    is performed using `torch.nn.functional.avg_pool2d`.
 
     Parameters
     ----------
@@ -1221,8 +1226,9 @@ class AveragePooling(Pool):
 
     Notes
     -----
-    Calling this feature returns a `np.ndarray` by default. If
-    `store_properties` is set to `True`, the returned array will be
+    Calling this feature returns a pooled image of the input, it will return
+    either numpy or torch depending on the backend. If `store_properties` is
+    set to `True` and the input is a numpy array, the returned array will be
     automatically wrapped in an `Image` object. This behavior is handled
     internally and does not affect the return type of the `get()` method.
 
@@ -1235,7 +1241,9 @@ def __init__(
     ):
         """Initialize the parameters for average pooling.
 
-        This constructor initializes the parameters for average pooling.
+        This constructor initializes the parameters for average pooling and
+        checks whether to use the numpy or torch implementation, defaults to
+        numpy.
 
         Parameters
         ----------
@@ -1248,6 +1256,110 @@ def __init__(
 
         super().__init__(np.mean, ksize=ksize, **kwargs)
 
+    def _get_numpy(
+        self,
+        image: NDArray,
+        ksize: int = 3,
+        **kwargs,
+    ):
+        """Method to perform average pooling with the numpy backend enabled.
+
+        Returns the result of the image passed to the scikit image block_reduce
+        function with `np.mean()` as the pooling function.
+
+        Parameters
+        ----------
+        image: NDArray
+            Input image to be pooled.
+        ksize: int
+            Kernel size of the pooling operation.
+
+        Returns
+        -------
+        NDArray
+            The pooled image as a `NDArray`.
+
+        """
+        return utils.safe_call(
+            skimage.measure.block_reduce,
+            image=image,
+            func=self.pooling, # This will be np.mean for this class.
+            block_size=ksize,
+            **kwargs,
+        )
+
+    def _get_torch(
+        self,
+        image: torch.Tensor,
+        ksize: int=3,
+        **kwargs,
+    ):
+        """Method to perform average pooling with the torch backend enabled.
+
+        Returns the result of the image passed to a torch average
+        pooling layer.
+
+        Parameters
+        ----------
+        image: torch.Tensor
+            Input image to be pooled.
+        ksize: int
+            Kernel size of the pooling operation.
+
+        Returns
+        -------
+        torch.Tensor
+            The pooled image as a `torch.Tensor`.
+
+        """
+
+        # If needed, expand tensor shape
+        if len(image.shape) == 2:
+            expanded_image = image.unsqueeze(0)
+
+            pooled_image = torch.nn.functional.avg_pool2d(
+                expanded_image, kernel_size=ksize,
+            )
+            # Remove the expanded dim.
+            return pooled_image.squeeze(0)
+
+        return torch.nn.functional.avg_pool2d(
+            image,
+            kernel_size=ksize,
+        )
+
+    def get(
+        self,
+        image: NDArray | torch.Tensor,
+        ksize: int=3,
+        **kwargs,
+    ):
+        """Method to perform pooling with either torch or numpy backend.
+
+        Checks the current backend and chooses the appropriate function to pool
+        the input image, either `_get_torch` or `_get_numpy`.
+
+        Parameters
+        ----------
+        image: NDArray | torch.Tensor
+            Input image to be pooled.
+        ksize: int
+            Kernel size of the pooling operation.
+
+        Returns
+        -------
+        NDArray | torch.Tensor
+            The pooled image as `NDArray` or `torch.Tensor` depending on
+            the backend.
+
+        """
+        if self.get_backend() == "numpy":
+            return self._get_numpy(image, ksize, **kwargs,)
+        elif self.get_backend() == "torch":
+            return self._get_torch(image, ksize, **kwargs,)
+        else:
+            raise NotImplementedError(f"Backend {self.backend} not supported")
+
 
 #TODO ***AL*** revise MaxPooling - torch, typing, docstring, unit test
 class MaxPooling(Pool):

deeptrack/tests/test_math.py

@@ -82,12 +82,28 @@ def test_Blur(self):
         #blurred_image = feature.resolve(input_image)
         #self.assertTrue(xp.all(blurred_image == expected_output))
 
+    def test_AveragePooling(self):
+        input_image = np.array([[1, 2, 3, 4], [5, 6, 7, 8]], dtype=float)
+        feature = math.AveragePooling(ksize=2)
+        pooled_image = feature.resolve(input_image)
+        self.assertTrue(np.all(pooled_image == [[3.5, 5.5]]))
+
 
 # Extending the test and setting the backend to torch
 @unittest.skipUnless(TORCH_AVAILABLE, "PyTorch is not installed.")
 class TestMath_Torch(TestMath_Numpy):
     BACKEND = "torch"
-    pass
+
+    def test_AveragePooling(self):
+        input_image = torch.tensor([[[ [1.0, 2.0, 3.0, 4.0],
+                                        [5.0, 6.0, 7.0, 8.0] ]]])
+        feature = math.AveragePooling(ksize=2)
+        pooled_image = feature(input_image, ksize=2)
+        expected = torch.tensor([[[[3.5, 5.5]]]])
+        self.assertEqual(pooled_image.shape, expected.shape)
+        self.assertTrue(torch.allclose(pooled_image, expected))
+
+
 
 
 class TestMath(unittest.TestCase):
@@ -109,6 +125,7 @@ def test_AveragePooling(self):
         pooled_image = feature.resolve(input_image)
         self.assertTrue(np.all(pooled_image == [[3.5, 5.5]]))
 
+
     def test_MaxPooling(self):
         input_image = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
         feature = math.MaxPooling(ksize=2)