Merge branch 'main' into fix-shear-autoaugment

Author: datumbox

.circleci/config.yml

@@ -351,7 +351,7 @@ jobs:
       - install_torchvision
       - install_prototype_dependencies
       - pip_install:
-          args: scipy pycocotools
+          args: scipy pycocotools h5py
           descr: Install optional dependencies
       - run:
           name: Enable prototype tests

.circleci/config.yml.in

@@ -43,6 +43,7 @@
     "module: video",
     "Perf",
     "Revert(ed)",
+    "topic: build",
 }
 
 

.github/process_commit.py

@@ -15,5 +15,6 @@ vizualization <sphx_glr_auto_examples_plot_visualization_utils.py>`.
     draw_bounding_boxes
     draw_segmentation_masks
     draw_keypoints
+    flow_to_image
     make_grid
     save_image

docs/source/utils.rst

@@ -156,7 +156,7 @@ def convert_to_coco_api(ds):
         img_dict["height"] = img.shape[-2]
         img_dict["width"] = img.shape[-1]
         dataset["images"].append(img_dict)
-        bboxes = targets["boxes"]
+        bboxes = targets["boxes"].clone()
         bboxes[:, 2:] -= bboxes[:, :2]
         bboxes = bboxes.tolist()
         labels = targets["labels"].tolist()

references/detection/coco_utils.py

@@ -2,6 +2,7 @@
 import csv
 import functools
 import gzip
+import io
 import itertools
 import json
 import lzma
@@ -1312,3 +1313,30 @@ def svhn(info, root, config):
         },
     )
     return num_samples
+
+
+@register_mock
+def pcam(info, root, config):
+    import h5py
+
+    num_images = {"train": 2, "test": 3, "val": 4}[config.split]
+
+    split = "valid" if config.split == "val" else config.split
+
+    images_io = io.BytesIO()
+    with h5py.File(images_io, "w") as f:
+        f["x"] = np.random.randint(0, 256, size=(num_images, 10, 10, 3), dtype=np.uint8)
+
+    targets_io = io.BytesIO()
+    with h5py.File(targets_io, "w") as f:
+        f["y"] = np.random.randint(0, 2, size=(num_images, 1, 1, 1), dtype=np.uint8)
+
+    # Create .gz compressed files
+    images_file = root / f"camelyonpatch_level_2_split_{split}_x.h5.gz"
+    targets_file = root / f"camelyonpatch_level_2_split_{split}_y.h5.gz"
+    for compressed_file_name, uncompressed_file_io in ((images_file, images_io), (targets_file, targets_io)):
+        compressed_data = gzip.compress(uncompressed_file_io.getbuffer())
+        with open(compressed_file_name, "wb") as compressed_file:
+            compressed_file.write(compressed_data)
+
+    return num_images

test/assets/expected_flow.pt

@@ -143,6 +143,17 @@ def test_forward_negative_sample_retinanet(self):
 
         assert_equal(loss_dict["bbox_regression"], torch.tensor(0.0))
 
+    def test_forward_negative_sample_fcos(self):
+        model = torchvision.models.detection.fcos_resnet50_fpn(
+            num_classes=2, min_size=100, max_size=100, pretrained_backbone=False
+        )
+
+        images, targets = self._make_empty_sample()
+        loss_dict = model(images, targets)
+
+        assert_equal(loss_dict["bbox_regression"], torch.tensor(0.0))
+        assert_equal(loss_dict["bbox_ctrness"], torch.tensor(0.0))
+
     def test_forward_negative_sample_ssd(self):
         model = torchvision.models.detection.ssd300_vgg16(num_classes=2, pretrained_backbone=False)
 

test/builtin_dataset_mocks.py

@@ -18,7 +18,7 @@ def test_home(mocker, tmp_path):
 
 
 def test_coverage():
-    untested_datasets = set(datasets.list()) - DATASET_MOCKS.keys()
+    untested_datasets = set(datasets.list_datasets()) - DATASET_MOCKS.keys()
     if untested_datasets:
         raise AssertionError(
             f"The dataset(s) {sequence_to_str(sorted(untested_datasets), separate_last='and ')} "

test/test_models_detection_negative_samples.py

@@ -317,5 +317,30 @@ def test_draw_keypoints_errors():
         utils.draw_keypoints(image=img, keypoints=invalid_keypoints)
 
 
+def test_flow_to_image():
+    h, w = 100, 100
+    flow = torch.meshgrid(torch.arange(h), torch.arange(w), indexing="ij")
+    flow = torch.stack(flow[::-1], dim=0).float()
+    flow[0] -= h / 2
+    flow[1] -= w / 2
+    img = utils.flow_to_image(flow)
+    path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "assets", "expected_flow.pt")
+    expected_img = torch.load(path, map_location="cpu")
+    assert_equal(expected_img, img)
+
+
+def test_flow_to_image_errors():
+    wrong_flow1 = torch.full((3, 10, 10), 0, dtype=torch.float)
+    wrong_flow2 = torch.full((2, 10), 0, dtype=torch.float)
+    wrong_flow3 = torch.full((2, 10, 30), 0, dtype=torch.int)
+
+    with pytest.raises(ValueError, match="Input flow should have shape"):
+        utils.flow_to_image(flow=wrong_flow1)
+    with pytest.raises(ValueError, match="Input flow should have shape"):
+        utils.flow_to_image(flow=wrong_flow2)
+    with pytest.raises(ValueError, match="Flow should be of dtype torch.float"):
+        utils.flow_to_image(flow=wrong_flow3)
+
+
 if __name__ == "__main__":
     pytest.main([__file__])