Update the comment of the num_classes parameter of deeplab v3 (#2071)

* Update deeplab_v3_plus.py

Update the comment of the `num_classes`parameter which contains the background class and the classes from the data.

* Update deeplab_v3_plus_test.py

Update the tests following the updating of 'num_classes' parameter (now including the background class)

keras_cv/models/segmentation/deeplab_v3_plus/deeplab_v3_plus.py

@@ -46,7 +46,7 @@ class DeepLabV3Plus(Task):
             somewhat sensible backbone to use in many cases is the
             `keras_cv.models.ResNet50V2Backbone.from_preset("resnet50_v2_imagenet")`.
         num_classes: int, the number of classes for the detection model. Note
-            that the `num_classes` doesn't contain the background class, and the
+            that the `num_classes` contains the background class, and the
             classes from the data should be represented by integers with range
             [0, `num_classes`).
         projection_filters: int, number of filters in the convolution layer

keras_cv/models/segmentation/deeplab_v3_plus/deeplab_v3_plus_test.py

@@ -32,7 +32,7 @@
 class DeepLabV3PlusTest(TestCase):
     def test_deeplab_v3_plus_construction(self):
         backbone = ResNet18V2Backbone(input_shape=[512, 512, 3])
-        model = DeepLabV3Plus(backbone=backbone, num_classes=1)
+        model = DeepLabV3Plus(backbone=backbone, num_classes=2)
         model.compile(
             optimizer="adam",
             loss=keras.losses.BinaryCrossentropy(),
@@ -42,7 +42,7 @@ def test_deeplab_v3_plus_construction(self):
     @pytest.mark.large
     def test_deeplab_v3_plus_call(self):
         backbone = ResNet18V2Backbone(input_shape=[512, 512, 3])
-        model = DeepLabV3Plus(backbone=backbone, num_classes=1)
+        model = DeepLabV3Plus(backbone=backbone, num_classes=2)
         images = np.random.uniform(size=(2, 512, 512, 3))
         _ = model(images)
         _ = model.predict(images)
@@ -83,7 +83,7 @@ def test_saved_model(self, save_format, filename):
         target_size = [512, 512, 3]
 
         backbone = ResNet18V2Backbone(input_shape=target_size)
-        model = DeepLabV3Plus(backbone=backbone, num_classes=1)
+        model = DeepLabV3Plus(backbone=backbone, num_classes=2)
 
         input_batch = np.ones(shape=[2] + target_size)
         model_output = model(input_batch)