diff --git a/test/test_models.py b/test/test_models.py
index 1c0b4892209..24b5a8b6b66 100644
--- a/test/test_models.py
+++ b/test/test_models.py
@@ -248,6 +248,25 @@ def test_fasterrcnn_switch_devices(self):
         self.assertTrue("scores" in out_cpu[0])
         self.assertTrue("labels" in out_cpu[0])
 
+    def test_generalizedrcnn_transform_repr(self):
+
+        min_size, max_size = 224, 299
+        image_mean = [0.485, 0.456, 0.406]
+        image_std = [0.229, 0.224, 0.225]
+
+        t = models.detection.transform.GeneralizedRCNNTransform(min_size=min_size,
+                                                                max_size=max_size,
+                                                                image_mean=image_mean,
+                                                                image_std=image_std)
+
+        # Check integrity of object __repr__ attribute
+        expected_string = 'GeneralizedRCNNTransform('
+        _indent = '\n    '
+        expected_string += '{0}Normalize(mean={1}, std={2})'.format(_indent, image_mean, image_std)
+        expected_string += '{0}Resize(min_size=({1},), max_size={2}, '.format(_indent, min_size, max_size)
+        expected_string += "mode='bilinear')\n)"
+        self.assertEqual(t.__repr__(), expected_string)
+
 
 for model_name in get_available_classification_models():
     # for-loop bodies don't define scopes, so we have to save the variables
diff --git a/torchvision/models/detection/transform.py b/torchvision/models/detection/transform.py
index f1cf8a41bfd..9b2ef009cb8 100644
--- a/torchvision/models/detection/transform.py
+++ b/torchvision/models/detection/transform.py
@@ -181,6 +181,15 @@ def postprocess(self, result, image_shapes, original_image_sizes):
                 result[i]["keypoints"] = keypoints
         return result
 
+    def __repr__(self):
+        format_string = self.__class__.__name__ + '('
+        _indent = '\n    '
+        format_string += "{0}Normalize(mean={1}, std={2})".format(_indent, self.image_mean, self.image_std)
+        format_string += "{0}Resize(min_size={1}, max_size={2}, mode='bilinear')".format(_indent, self.min_size,
+                                                                                         self.max_size)
+        format_string += '\n)'
+        return format_string
+
 
 def resize_keypoints(keypoints, original_size, new_size):
     # type: (Tensor, List[int], List[int])