fix prototype datasets data loading tests

.circleci/config.yml.in

@@ -152,11 +152,10 @@ commands:
           args: --no-build-isolation <<# parameters.editable >> --editable <</ parameters.editable >> .
           descr: Install torchvision <<# parameters.editable >> in editable mode <</ parameters.editable >>
 
+  # Installs all extra dependencies that are needed in the torchvision.prototype namespace, but are not tracked in the
+  # project requirements.
   install_prototype_dependencies:
     steps:
-      - pip_install:
-          args: iopath
-          descr: Install third-party dependencies
       - pip_install:
           args: --pre torchdata --extra-index-url https://download.pytorch.org/whl/nightly/cpu
           descr: Install torchdata from nightly releases
@@ -366,7 +365,7 @@ jobs:
       - install_torchvision
       - install_prototype_dependencies
       - pip_install:
-          args: scipy pycocotools h5py
+          args: scipy pycocotools h5py dill
           descr: Install optional dependencies
       - run_tests_selective:
           file_or_dir: test/test_prototype_*.py

test/test_prototype_builtin_datasets.py

@@ -7,6 +7,7 @@
 import torch
 from builtin_dataset_mocks import parametrize_dataset_mocks, DATASET_MOCKS
 from torch.testing._comparison import assert_equal, TensorLikePair, ObjectPair
+from torch.utils.data._utils.serialization import DILL_AVAILABLE
 from torch.utils.data.graph import traverse
 from torch.utils.data.graph_settings import get_all_graph_pipes
 from torchdata.datapipes.iter import Shuffler, ShardingFilter
@@ -109,19 +110,27 @@ def test_transformable(self, test_home, dataset_mock, config):
 
         next(iter(dataset.map(transforms.Identity())))
 
-    @pytest.mark.xfail(reason="See https://github.com/pytorch/data/issues/237")
     @parametrize_dataset_mocks(DATASET_MOCKS)
-    def test_serializable(self, test_home, dataset_mock, config):
+    def test_serializable_pickle(self, test_home, dataset_mock, config):
         dataset_mock.prepare(test_home, config)
-
         dataset = datasets.load(dataset_mock.name, **config)
 
         pickle.dumps(dataset)
 
+    @pytest.mark.skipif(not DILL_AVAILABLE, reason="Package `dill` is not available.")
+    # TODO: remove this as soon as dill is fully supported
+    @pytest.mark.xfail(reason="See https://github.com/pytorch/data/issues/237")
+    def test_serializable_dill(self, test_home, dataset_mock, config):
+        import dill
+
+        dataset_mock.prepare(test_home, config)
+        dataset = datasets.load(dataset_mock.name, **config)
+
+        dill.dumps(dataset)
+
     # TODO: we need to enforce not only that both a Shuffler and a ShardingFilter are part of the datapipe, but also
     #  that the Shuffler comes before the ShardingFilter. Early commits in https://github.com/pytorch/vision/pull/5680
     #  contain a custom test for that, but we opted to wait for a potential solution / test from torchdata for now.
-    @pytest.mark.xfail(reason="See https://github.com/pytorch/data/issues/237")
     @parametrize_dataset_mocks(DATASET_MOCKS)
     @pytest.mark.parametrize("annotation_dp_type", (Shuffler, ShardingFilter))
     def test_has_annotations(self, test_home, dataset_mock, config, annotation_dp_type):