Merge branch 'main' into context2task

examples/advanced-pytorch/client.py

@@ -110,7 +110,7 @@ def main() -> None:
     )
     parser.add_argument(
         "--toy",
-        action='store_true',
+        action="store_true",
         help="Set to true to quicky run the client using only 10 datasamples. \
         Useful for testing purposes. Default: False",
     )

examples/advanced-pytorch/server.py

@@ -76,7 +76,7 @@ def main():
     parser = argparse.ArgumentParser(description="Flower")
     parser.add_argument(
         "--toy",
-        action='store_true',
+        action="store_true",
         help="Set to true to use only 10 datasamples for validation. \
             Useful for testing purposes. Default: False",
     )

examples/advanced-pytorch/utils.py

@@ -28,18 +28,21 @@ def load_centralized_data():
 
 def apply_transforms(batch):
     """Apply transforms to the partition from FederatedDataset."""
-    pytorch_transforms = Compose([
-        Resize(256),
-        CenterCrop(224),
-        ToTensor(),
-        Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-    ])
+    pytorch_transforms = Compose(
+        [
+            Resize(256),
+            CenterCrop(224),
+            ToTensor(),
+            Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+        ]
+    )
     batch["img"] = [pytorch_transforms(img) for img in batch["img"]]
     return batch
 
 
-def train(net, trainloader, valloader, epochs,
-          device: torch.device = torch.device("cpu")):
+def train(
+    net, trainloader, valloader, epochs, device: torch.device = torch.device("cpu")
+):
     """Train the network on the training set."""
     print("Starting training...")
     net.to(device)  # move model to GPU if available
@@ -71,8 +74,9 @@ def train(net, trainloader, valloader, epochs,
     return results
 
 
-def test(net, testloader, steps: int = None,
-         device: torch.device = torch.device("cpu")):
+def test(
+    net, testloader, steps: int = None, device: torch.device = torch.device("cpu")
+):
     """Validate the network on the entire test set."""
     print("Starting evalutation...")
     net.to(device)  # move model to GPU if available

examples/advanced-tensorflow/client.py

@@ -86,7 +86,7 @@ def main() -> None:
     )
     parser.add_argument(
         "--toy",
-        action='store_true',
+        action="store_true",
         help="Set to true to quicky run the client using only 10 datasamples. "
         "Useful for testing purposes. Default: False",
     )

examples/quickstart-huggingface/client.py

@@ -119,7 +119,7 @@ def evaluate(self, parameters, config):
         required=True,
         type=int,
         help="Partition of the dataset divided into 1,000 iid partitions created "
-             "artificially.",
+        "artificially.",
     )
     node_id = parser.parse_args().node_id
     main(node_id)

examples/vertical-fl/README.md

@@ -295,7 +295,7 @@ class ServerModel(nn.Module):
 
 It comprises a single linear layer that accepts the concatenated outputs from
 all client models as its input. The number of inputs to this layer equals the
-total number of outputs from the client models ( $3 \times 4 = 12$ ). After processing
+total number of outputs from the client models (3 x 4 = 12). After processing
 these inputs, the linear layer's output is passed through a sigmoid activation
 function (`nn.Sigmoid()`), which maps the result to a `(0, 1)` range, providing
 a probability score indicative of the likelihood of survival.