Merge main

adap · Jul 25, 2024 · 66fde74 · 66fde74
2 parents da9518b + fb744a2
commit 66fde74
Show file tree

Hide file tree

Showing 2 changed files with 35 additions and 3 deletions.
diff --git a/datasets/doc/source/tutorial-quickstart.ipynb b/datasets/doc/source/tutorial-quickstart.ipynb
@@ -439,6 +439,36 @@
                 "dataloader = DataLoader(partition_torch, batch_size=64)"
             ]
         },
+        {
+            "cell_type": "markdown",
+            "id": "b93678a5",
+            "metadata": {},
+            "source": "The `Dataloader` created this way does not return a `Tuple` when iterating over it but a `Dict` with the names of the columns as keys and features as values. Look below for an example."
+        },
+        {
+            "cell_type": "code",
+            "execution_count": null,
+            "id": "5edd3ce2",
+            "metadata": {},
+            "outputs": [
+                {
+                    "name": "stdout",
+                    "output_type": "stream",
+                    "text": [
+                        "Return type when iterating over dataloader: <class 'dict'>\n",
+                        "torch.Size([64, 3, 32, 32])\n",
+                        "torch.Size([64])\n"
+                    ]
+                }
+            ],
+            "source": [
+                "for batch in dataloader:\n",
+                "    print(f\"Return type when iterating over a dataloader: {type(batch)}\")\n",
+                "    print(batch[\"img\"].shape)\n",
+                "    print(batch[\"label\"].shape)\n",
+                "    break"
+            ]
+        },
         {
             "cell_type": "markdown",
             "id": "71531613",

diff --git a/datasets/flwr_datasets/federated_dataset.py b/datasets/flwr_datasets/federated_dataset.py
@@ -54,9 +54,11 @@ class FederatedDataset:
         no operation is applied.
     partitioners : Dict[str, Union[Partitioner, int]]
         A dictionary mapping the Dataset split (a `str`) to a `Partitioner` or an `int`
-        (representing the number of IID partitions that this split should be partitioned
-        into). One or multiple `Partitioner` objects can be specified in that manner,
-        but at most, one per split.
+        (representing the number of IID partitions that this split should be
+        partitioned into, i.e., using the default partitioner
+        `IidPartitioner <https://flower.ai/docs/datasets/ref-api/flwr_
+        datasets.partitioner.IidPartitioner.html>`_). One or multiple `Partitioner`
+        objects can be specified in that manner, but at most, one per split.
     shuffle : bool
         Whether to randomize the order of samples. Applied prior to preprocessing
         operations, speratelly to each of the present splits in the dataset. It uses