separate transforms v2 legacy test utils (#7842)

test/prototype_common_utils.py

@@ -4,12 +4,12 @@
 
 import pytest
 import torch
-
-from common_utils import combinations_grid, DEFAULT_EXTRA_DIMS, from_loader, from_loaders, TensorLoader
 from torch.nn.functional import one_hot
 
 from torchvision.prototype import datapoints
 
+from transforms_v2_legacy_utils import combinations_grid, DEFAULT_EXTRA_DIMS, from_loader, from_loaders, TensorLoader
+
 
 @dataclasses.dataclass
 class LabelLoader(TensorLoader):

test/test_datapoints.py

@@ -2,7 +2,7 @@
 
 import pytest
 import torch
-from common_utils import assert_equal, make_bounding_box, make_image, make_segmentation_mask, make_video
+from common_utils import assert_equal, make_bounding_boxes, make_image, make_segmentation_mask, make_video
 from PIL import Image
 
 from torchvision import datapoints
@@ -68,7 +68,7 @@ def test_new_requires_grad(data, input_requires_grad, expected_requires_grad):
     assert datapoint.requires_grad is expected_requires_grad
 
 
-@pytest.mark.parametrize("make_input", [make_image, make_bounding_box, make_segmentation_mask, make_video])
+@pytest.mark.parametrize("make_input", [make_image, make_bounding_boxes, make_segmentation_mask, make_video])
 def test_isinstance(make_input):
     assert isinstance(make_input(), torch.Tensor)
 
@@ -80,7 +80,7 @@ def test_wrapping_no_copy():
     assert image.data_ptr() == tensor.data_ptr()
 
 
-@pytest.mark.parametrize("make_input", [make_image, make_bounding_box, make_segmentation_mask, make_video])
+@pytest.mark.parametrize("make_input", [make_image, make_bounding_boxes, make_segmentation_mask, make_video])
 def test_to_wrapping(make_input):
     dp = make_input()
 
@@ -90,7 +90,7 @@ def test_to_wrapping(make_input):
     assert dp_to.dtype is torch.float64
 
 
-@pytest.mark.parametrize("make_input", [make_image, make_bounding_box, make_segmentation_mask, make_video])
+@pytest.mark.parametrize("make_input", [make_image, make_bounding_boxes, make_segmentation_mask, make_video])
 @pytest.mark.parametrize("return_type", ["Tensor", "datapoint"])
 def test_to_datapoint_reference(make_input, return_type):
     tensor = torch.rand((3, 16, 16), dtype=torch.float64)
@@ -104,7 +104,7 @@ def test_to_datapoint_reference(make_input, return_type):
     assert type(tensor) is torch.Tensor
 
 
-@pytest.mark.parametrize("make_input", [make_image, make_bounding_box, make_segmentation_mask, make_video])
+@pytest.mark.parametrize("make_input", [make_image, make_bounding_boxes, make_segmentation_mask, make_video])
 @pytest.mark.parametrize("return_type", ["Tensor", "datapoint"])
 def test_clone_wrapping(make_input, return_type):
     dp = make_input()
@@ -116,7 +116,7 @@ def test_clone_wrapping(make_input, return_type):
     assert dp_clone.data_ptr() != dp.data_ptr()
 
 
-@pytest.mark.parametrize("make_input", [make_image, make_bounding_box, make_segmentation_mask, make_video])
+@pytest.mark.parametrize("make_input", [make_image, make_bounding_boxes, make_segmentation_mask, make_video])
 @pytest.mark.parametrize("return_type", ["Tensor", "datapoint"])
 def test_requires_grad__wrapping(make_input, return_type):
     dp = make_input(dtype=torch.float)
@@ -131,7 +131,7 @@ def test_requires_grad__wrapping(make_input, return_type):
     assert dp_requires_grad.requires_grad
 
 
-@pytest.mark.parametrize("make_input", [make_image, make_bounding_box, make_segmentation_mask, make_video])
+@pytest.mark.parametrize("make_input", [make_image, make_bounding_boxes, make_segmentation_mask, make_video])
 @pytest.mark.parametrize("return_type", ["Tensor", "datapoint"])
 def test_detach_wrapping(make_input, return_type):
     dp = make_input(dtype=torch.float).requires_grad_(True)
@@ -170,7 +170,7 @@ def test_force_subclass_with_metadata(return_type):
     datapoints.set_return_type("tensor")
 
 
-@pytest.mark.parametrize("make_input", [make_image, make_bounding_box, make_segmentation_mask, make_video])
+@pytest.mark.parametrize("make_input", [make_image, make_bounding_boxes, make_segmentation_mask, make_video])
 @pytest.mark.parametrize("return_type", ["Tensor", "datapoint"])
 def test_other_op_no_wrapping(make_input, return_type):
     dp = make_input()
@@ -182,7 +182,7 @@ def test_other_op_no_wrapping(make_input, return_type):
     assert type(output) is (type(dp) if return_type == "datapoint" else torch.Tensor)
 
 
-@pytest.mark.parametrize("make_input", [make_image, make_bounding_box, make_segmentation_mask, make_video])
+@pytest.mark.parametrize("make_input", [make_image, make_bounding_boxes, make_segmentation_mask, make_video])
 @pytest.mark.parametrize(
     "op",
     [
@@ -199,7 +199,7 @@ def test_no_tensor_output_op_no_wrapping(make_input, op):
     assert type(output) is not type(dp)
 
 
-@pytest.mark.parametrize("make_input", [make_image, make_bounding_box, make_segmentation_mask, make_video])
+@pytest.mark.parametrize("make_input", [make_image, make_bounding_boxes, make_segmentation_mask, make_video])
 @pytest.mark.parametrize("return_type", ["Tensor", "datapoint"])
 def test_inplace_op_no_wrapping(make_input, return_type):
     dp = make_input()
@@ -212,7 +212,7 @@ def test_inplace_op_no_wrapping(make_input, return_type):
     assert type(dp) is original_type
 
 
-@pytest.mark.parametrize("make_input", [make_image, make_bounding_box, make_segmentation_mask, make_video])
+@pytest.mark.parametrize("make_input", [make_image, make_bounding_boxes, make_segmentation_mask, make_video])
 def test_wrap(make_input):
     dp = make_input()
 
@@ -225,7 +225,7 @@ def test_wrap(make_input):
     assert dp_new.data_ptr() == output.data_ptr()
 
 
-@pytest.mark.parametrize("make_input", [make_image, make_bounding_box, make_segmentation_mask, make_video])
+@pytest.mark.parametrize("make_input", [make_image, make_bounding_boxes, make_segmentation_mask, make_video])
 @pytest.mark.parametrize("requires_grad", [False, True])
 def test_deepcopy(make_input, requires_grad):
     dp = make_input(dtype=torch.float)
@@ -242,7 +242,7 @@ def test_deepcopy(make_input, requires_grad):
     assert dp_deepcopied.requires_grad is requires_grad
 
 
-@pytest.mark.parametrize("make_input", [make_image, make_bounding_box, make_segmentation_mask, make_video])
+@pytest.mark.parametrize("make_input", [make_image, make_bounding_boxes, make_segmentation_mask, make_video])
 @pytest.mark.parametrize("return_type", ["Tensor", "datapoint"])
 @pytest.mark.parametrize(
     "op",

test/test_prototype_transforms.py

@@ -4,21 +4,21 @@
 import pytest
 import torch
 
-from common_utils import (
-    assert_equal,
-    DEFAULT_EXTRA_DIMS,
-    make_bounding_box,
-    make_detection_mask,
-    make_image,
-    make_video,
-)
+from common_utils import assert_equal
 
 from prototype_common_utils import make_label
 
 from torchvision.datapoints import BoundingBoxes, BoundingBoxFormat, Image, Mask, Video
 from torchvision.prototype import datapoints, transforms
 from torchvision.transforms.v2.functional import clamp_bounding_boxes, InterpolationMode, pil_to_tensor, to_pil_image
 from torchvision.transforms.v2.utils import check_type, is_pure_tensor
+from transforms_v2_legacy_utils import (
+    DEFAULT_EXTRA_DIMS,
+    make_bounding_boxes,
+    make_detection_mask,
+    make_image,
+    make_video,
+)
 
 BATCH_EXTRA_DIMS = [extra_dims for extra_dims in DEFAULT_EXTRA_DIMS if extra_dims]
 
@@ -167,7 +167,7 @@ def test__get_params(self, mocker):
 
         flat_inputs = [
             make_image(size=canvas_size, color_space="RGB"),
-            make_bounding_box(format=BoundingBoxFormat.XYXY, canvas_size=canvas_size, batch_dims=batch_shape),
+            make_bounding_boxes(format=BoundingBoxFormat.XYXY, canvas_size=canvas_size, batch_dims=batch_shape),
         ]
         params = transform._get_params(flat_inputs)
 
@@ -202,7 +202,7 @@ def test__transform_culling(self, mocker):
             ),
         )
 
-        bounding_boxes = make_bounding_box(
+        bounding_boxes = make_bounding_boxes(
             format=BoundingBoxFormat.XYXY, canvas_size=canvas_size, batch_dims=(batch_size,)
         )
         masks = make_detection_mask(size=canvas_size, batch_dims=(batch_size,))
@@ -240,7 +240,7 @@ def test__transform_bounding_boxes_clamping(self, mocker):
             ),
         )
 
-        bounding_boxes = make_bounding_box(
+        bounding_boxes = make_bounding_boxes(
             format=BoundingBoxFormat.XYXY, canvas_size=canvas_size, batch_dims=(batch_size,)
         )
         mock = mocker.patch(
@@ -283,7 +283,7 @@ class TestPermuteDimensions:
     def test_call(self, dims, inverse_dims):
         sample = dict(
             image=make_image(),
-            bounding_boxes=make_bounding_box(format=BoundingBoxFormat.XYXY),
+            bounding_boxes=make_bounding_boxes(format=BoundingBoxFormat.XYXY),
             video=make_video(),
             str="str",
             int=0,
@@ -327,7 +327,7 @@ class TestTransposeDimensions:
     def test_call(self, dims):
         sample = dict(
             image=make_image(),
-            bounding_boxes=make_bounding_box(format=BoundingBoxFormat.XYXY),
+            bounding_boxes=make_bounding_boxes(format=BoundingBoxFormat.XYXY),
             video=make_video(),
             str="str",
             int=0,
@@ -389,7 +389,7 @@ def make_datapoints():
 
         pil_image = to_pil_image(make_image(size=size, color_space="RGB"))
         target = {
-            "boxes": make_bounding_box(canvas_size=size, format="XYXY", batch_dims=(num_objects,), dtype=torch.float),
+            "boxes": make_bounding_boxes(canvas_size=size, format="XYXY", batch_dims=(num_objects,), dtype=torch.float),
             "labels": make_label(extra_dims=(num_objects,), categories=80),
             "masks": make_detection_mask(size=size, num_objects=num_objects, dtype=torch.long),
         }
@@ -398,7 +398,7 @@ def make_datapoints():
 
         tensor_image = torch.Tensor(make_image(size=size, color_space="RGB"))
         target = {
-            "boxes": make_bounding_box(canvas_size=size, format="XYXY", batch_dims=(num_objects,), dtype=torch.float),
+            "boxes": make_bounding_boxes(canvas_size=size, format="XYXY", batch_dims=(num_objects,), dtype=torch.float),
             "labels": make_label(extra_dims=(num_objects,), categories=80),
             "masks": make_detection_mask(size=size, num_objects=num_objects, dtype=torch.long),
         }
@@ -407,7 +407,7 @@ def make_datapoints():
 
         datapoint_image = make_image(size=size, color_space="RGB")
         target = {
-            "boxes": make_bounding_box(canvas_size=size, format="XYXY", batch_dims=(num_objects,), dtype=torch.float),
+            "boxes": make_bounding_boxes(canvas_size=size, format="XYXY", batch_dims=(num_objects,), dtype=torch.float),
             "labels": make_label(extra_dims=(num_objects,), categories=80),
             "masks": make_detection_mask(size=size, num_objects=num_objects, dtype=torch.long),
         }

test/test_transforms_v2.py

@@ -11,25 +11,23 @@
 import torch
 import torchvision.transforms.v2 as transforms
 
-from common_utils import (
-    assert_equal,
-    assert_run_python_script,
-    cpu_and_cuda,
-    make_bounding_box,
+from common_utils import assert_equal, assert_run_python_script, cpu_and_cuda
+from torch.utils._pytree import tree_flatten, tree_unflatten
+from torchvision import datapoints
+from torchvision.ops.boxes import box_iou
+from torchvision.transforms.functional import to_pil_image
+from torchvision.transforms.v2 import functional as F
+from torchvision.transforms.v2.utils import check_type, is_pure_tensor, query_chw
+from transforms_v2_legacy_utils import (
     make_bounding_boxes,
     make_detection_mask,
     make_image,
     make_images,
+    make_multiple_bounding_boxes,
     make_segmentation_mask,
     make_video,
     make_videos,
 )
-from torch.utils._pytree import tree_flatten, tree_unflatten
-from torchvision import datapoints
-from torchvision.ops.boxes import box_iou
-from torchvision.transforms.functional import to_pil_image
-from torchvision.transforms.v2 import functional as F
-from torchvision.transforms.v2.utils import check_type, is_pure_tensor, query_chw
 
 
 def make_vanilla_tensor_images(*args, **kwargs):
@@ -45,7 +43,7 @@ def make_pil_images(*args, **kwargs):
 
 
 def make_vanilla_tensor_bounding_boxes(*args, **kwargs):
-    for bounding_boxes in make_bounding_boxes(*args, **kwargs):
+    for bounding_boxes in make_multiple_bounding_boxes(*args, **kwargs):
         yield bounding_boxes.data
 
 
@@ -180,13 +178,13 @@ def test_common(self, transform, adapter, container_type, image_or_video, device
             image_datapoint=make_image(size=canvas_size),
             video_datapoint=make_video(size=canvas_size),
             image_pil=next(make_pil_images(sizes=[canvas_size], color_spaces=["RGB"])),
-            bounding_boxes_xyxy=make_bounding_box(
+            bounding_boxes_xyxy=make_bounding_boxes(
                 format=datapoints.BoundingBoxFormat.XYXY, canvas_size=canvas_size, batch_dims=(3,)
             ),
-            bounding_boxes_xywh=make_bounding_box(
+            bounding_boxes_xywh=make_bounding_boxes(
                 format=datapoints.BoundingBoxFormat.XYWH, canvas_size=canvas_size, batch_dims=(4,)
             ),
-            bounding_boxes_cxcywh=make_bounding_box(
+            bounding_boxes_cxcywh=make_bounding_boxes(
                 format=datapoints.BoundingBoxFormat.CXCYWH, canvas_size=canvas_size, batch_dims=(5,)
             ),
             bounding_boxes_degenerate_xyxy=datapoints.BoundingBoxes(
@@ -813,7 +811,7 @@ def test__transform(self, mocker):
 
         size = (32, 24)
         image = make_image(size)
-        bboxes = make_bounding_box(format="XYXY", canvas_size=size, batch_dims=(6,))
+        bboxes = make_bounding_boxes(format="XYXY", canvas_size=size, batch_dims=(6,))
         masks = make_detection_mask(size, num_objects=6)
 
         sample = [image, bboxes, masks]

test/test_transforms_v2_consistency.py

@@ -12,17 +12,7 @@
 
 import torch
 import torchvision.transforms.v2 as v2_transforms
-from common_utils import (
-    ArgsKwargs,
-    assert_close,
-    assert_equal,
-    make_bounding_box,
-    make_detection_mask,
-    make_image,
-    make_images,
-    make_segmentation_mask,
-    set_rng_seed,
-)
+from common_utils import assert_close, assert_equal, set_rng_seed
 from torch import nn
 from torchvision import datapoints, transforms as legacy_transforms
 from torchvision._utils import sequence_to_str
@@ -32,6 +22,14 @@
 from torchvision.transforms.v2._utils import _get_fill
 from torchvision.transforms.v2.functional import to_pil_image
 from torchvision.transforms.v2.utils import query_size
+from transforms_v2_legacy_utils import (
+    ArgsKwargs,
+    make_bounding_boxes,
+    make_detection_mask,
+    make_image,
+    make_images,
+    make_segmentation_mask,
+)
 
 DEFAULT_MAKE_IMAGES_KWARGS = dict(color_spaces=["RGB"], extra_dims=[(4,)])
 
@@ -1090,7 +1088,7 @@ def make_label(extra_dims, categories):
 
         pil_image = to_pil_image(make_image(size=size, color_space="RGB"))
         target = {
-            "boxes": make_bounding_box(canvas_size=size, format="XYXY", batch_dims=(num_objects,), dtype=torch.float),
+            "boxes": make_bounding_boxes(canvas_size=size, format="XYXY", batch_dims=(num_objects,), dtype=torch.float),
             "labels": make_label(extra_dims=(num_objects,), categories=80),
         }
         if with_mask:
@@ -1100,7 +1098,7 @@ def make_label(extra_dims, categories):
 
         tensor_image = torch.Tensor(make_image(size=size, color_space="RGB", dtype=torch.float32))
         target = {
-            "boxes": make_bounding_box(canvas_size=size, format="XYXY", batch_dims=(num_objects,), dtype=torch.float),
+            "boxes": make_bounding_boxes(canvas_size=size, format="XYXY", batch_dims=(num_objects,), dtype=torch.float),
             "labels": make_label(extra_dims=(num_objects,), categories=80),
         }
         if with_mask:
@@ -1110,7 +1108,7 @@ def make_label(extra_dims, categories):
 
         datapoint_image = make_image(size=size, color_space="RGB", dtype=torch.float32)
         target = {
-            "boxes": make_bounding_box(canvas_size=size, format="XYXY", batch_dims=(num_objects,), dtype=torch.float),
+            "boxes": make_bounding_boxes(canvas_size=size, format="XYXY", batch_dims=(num_objects,), dtype=torch.float),
             "labels": make_label(extra_dims=(num_objects,), categories=80),
         }
         if with_mask: