test vis gradcam for binary classification task (#5654)

Follow up of issue #5530 #5528 and (closed) PR #5547

### Description

Add test case for a binary classification task in `test_vis_gradcam`

### Types of changes
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [x] Non-breaking change (fix or new feature that would not break
existing functionality).
- [x] New tests added to cover the changes.  
- [x] In-line docstrings updated.

Signed-off-by: Geevarghese George <thatgeeman@users.noreply.github.com>

Author: thatgeeman

monai/visualize/class_activation_maps.py

@@ -238,10 +238,10 @@ class CAM(CAMBase):
         result = cam(x=torch.rand((1, 1, 48, 64)))
 
         # resnet 2d
-        from monai.networks.nets import se_resnet50
+        from monai.networks.nets import seresnet50
         from monai.visualize import CAM
 
-        model_2d = se_resnet50(spatial_dims=2, in_channels=3, num_classes=4)
+        model_2d = seresnet50(spatial_dims=2, in_channels=3, num_classes=4)
         cam = CAM(nn_module=model_2d, target_layers="layer4", fc_layers="last_linear")
         result = cam(x=torch.rand((2, 3, 48, 64)))
 
@@ -339,10 +339,10 @@ class GradCAM(CAMBase):
         result = cam(x=torch.rand((1, 1, 48, 64)))
 
         # resnet 2d
-        from monai.networks.nets import se_resnet50
+        from monai.networks.nets import seresnet50
         from monai.visualize import GradCAM
 
-        model_2d = se_resnet50(spatial_dims=2, in_channels=3, num_classes=4)
+        model_2d = seresnet50(spatial_dims=2, in_channels=3, num_classes=4)
         cam = GradCAM(nn_module=model_2d, target_layers="layer4")
         result = cam(x=torch.rand((2, 3, 48, 64)))
 

tests/test_vis_gradcam.py

@@ -45,6 +45,19 @@ def __call__(self, x, adjoint_info):
             (2, 1, 48, 64),
         ]
     )
+    # 2D binary classification (out_channels=1)
+    TESTS.append(
+        [
+            cam,
+            {
+                "model": "densenet2d_bin",
+                "shape": (2, 1, 48, 64),
+                "feature_shape": (2, 1, 1, 2),
+                "target_layers": "class_layers.relu",
+            },
+            (2, 1, 48, 64),
+        ]
+    )
     # 3D
     TESTS.append(
         [
@@ -58,6 +71,19 @@ def __call__(self, x, adjoint_info):
             (2, 1, 6, 6, 6),
         ]
     )
+    # 3D binary classification (out_channels=1)
+    TESTS.append(
+        [
+            cam,
+            {
+                "model": "densenet3d_bin",
+                "shape": (2, 1, 6, 6, 6),
+                "feature_shape": (2, 1, 2, 2, 2),
+                "target_layers": "class_layers.relu",
+            },
+            (2, 1, 6, 6, 6),
+        ]
+    )
     # 2D
     TESTS.append(
         [
@@ -66,6 +92,14 @@ def __call__(self, x, adjoint_info):
             (2, 1, 64, 64),
         ]
     )
+    # 2D binary classification (num_classes=1)
+    TESTS.append(
+        [
+            cam,
+            {"model": "senet2d_bin", "shape": (2, 3, 64, 64), "feature_shape": (2, 1, 2, 2), "target_layers": "layer4"},
+            (2, 1, 64, 64),
+        ]
+    )
 
     # 3D
     TESTS.append(
@@ -80,6 +114,19 @@ def __call__(self, x, adjoint_info):
             (2, 1, 8, 8, 48),
         ]
     )
+    # 3D binary classification (num_classes=1)
+    TESTS.append(
+        [
+            cam,
+            {
+                "model": "senet3d_bin",
+                "shape": (2, 3, 8, 8, 48),
+                "feature_shape": (2, 1, 1, 1, 2),
+                "target_layers": "layer4",
+            },
+            (2, 1, 8, 8, 48),
+        ]
+    )
 
     # adjoint info
     TESTS.append(
@@ -103,14 +150,24 @@ class TestGradientClassActivationMap(unittest.TestCase):
     def test_shape(self, cam_class, input_data, expected_shape):
         if input_data["model"] == "densenet2d":
             model = DenseNet121(spatial_dims=2, in_channels=1, out_channels=3)
+        elif input_data["model"] == "densenet2d_bin":
+            model = DenseNet(spatial_dims=2, in_channels=1, out_channels=1)
         elif input_data["model"] == "densenet3d":
             model = DenseNet(
                 spatial_dims=3, in_channels=1, out_channels=3, init_features=2, growth_rate=2, block_config=(6,)
             )
+        elif input_data["model"] == "densenet3d_bin":
+            model = DenseNet(
+                spatial_dims=3, in_channels=1, out_channels=1, init_features=2, growth_rate=2, block_config=(6,)
+            )
         elif input_data["model"] == "senet2d":
             model = SEResNet50(spatial_dims=2, in_channels=3, num_classes=4)
+        elif input_data["model"] == "senet2d_bin":
+            model = SEResNet50(spatial_dims=2, in_channels=3, num_classes=1)
         elif input_data["model"] == "senet3d":
             model = SEResNet50(spatial_dims=3, in_channels=3, num_classes=4)
+        elif input_data["model"] == "senet3d_bin":
+            model = SEResNet50(spatial_dims=3, in_channels=3, num_classes=1)
         elif input_data["model"] == "adjoint":
             model = DenseNetAdjoint(spatial_dims=2, in_channels=1, out_channels=3)