init

baselines/fedbabu/.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

baselines/fedbabu/README.md

@@ -0,0 +1,20 @@
+# fedbabu: A Flower / PyTorch app
+
+## Install dependencies and project
+
+```bash
+pip install -e .
+```
+
+## Run with the Simulation Engine
+
+In the `fedbabu` directory, use `flwr run` to run a local simulation:
+
+```bash
+flwr run .
+```
+
+## Run with the Deployment Engine
+
+> \[!NOTE\]
+> An update to this example will show how to run this Flower application with the Deployment Engine and TLS certificates, or with Docker.

baselines/fedbabu/fedbabu/__init__.py

@@ -0,0 +1 @@
+"""fedbabu: A Flower / PyTorch app."""

baselines/fedbabu/fedbabu/client_app.py

@@ -0,0 +1,58 @@
+"""fedbabu: A Flower / PyTorch app."""
+
+import torch
+from flwr.client import NumPyClient, ClientApp
+from flwr.common import Context
+
+from fedbabu.task import (
+    Net,
+    load_data,
+    get_weights,
+    set_weights,
+    train,
+    test,
+)
+
+
+# Define Flower Client and client_fn
+class FlowerClient(NumPyClient):
+    def __init__(self, net, trainloader, valloader, local_epochs):
+        self.net = net
+        self.trainloader = trainloader
+        self.valloader = valloader
+        self.local_epochs = local_epochs
+        self.device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+        self.net.to(self.device)
+
+    def fit(self, parameters, config):
+        set_weights(self.net, parameters)
+        train_loss = train(
+            self.net,
+            self.trainloader,
+            self.local_epochs,
+            self.device,
+        )
+        return get_weights(self.net), len(self.trainloader.dataset), {"train_loss": train_loss}
+
+    def evaluate(self, parameters, config):
+        set_weights(self.net, parameters)
+        loss, accuracy = test(self.net, self.valloader, self.device)
+        return loss, len(self.valloader.dataset), {"accuracy": accuracy}
+
+
+def client_fn(context: Context):
+    # Load model and data
+    net = Net()
+    partition_id = context.node_config["partition-id"]
+    num_partitions = context.node_config["num-partitions"]
+    trainloader, valloader = load_data(partition_id, num_partitions)
+    local_epochs = context.run_config["local-epochs"]
+
+    # Return Client instance
+    return FlowerClient(net, trainloader, valloader, local_epochs).to_client()
+
+
+# Flower ClientApp
+app = ClientApp(
+    client_fn,
+)

baselines/fedbabu/fedbabu/server_app.py

@@ -0,0 +1,31 @@
+"""fedbabu: A Flower / PyTorch app."""
+
+from flwr.common import Context, ndarrays_to_parameters
+from flwr.server import ServerApp, ServerAppComponents, ServerConfig
+from flwr.server.strategy import FedAvg
+
+from fedbabu.task import Net, get_weights
+
+
+def server_fn(context: Context):
+    # Read from config
+    num_rounds = context.run_config["num-server-rounds"]
+    fraction_fit = context.run_config["fraction-fit"]
+
+    # Initialize model parameters
+    ndarrays = get_weights(Net())
+    parameters = ndarrays_to_parameters(ndarrays)
+
+    # Define strategy
+    strategy = FedAvg(
+        fraction_fit=fraction_fit,
+        fraction_evaluate=1.0,
+        min_available_clients=2,
+        initial_parameters=parameters,
+    )
+    config = ServerConfig(num_rounds=num_rounds)
+
+    return ServerAppComponents(strategy=strategy, config=config)
+
+# Create ServerApp
+app = ServerApp(server_fn=server_fn)

baselines/fedbabu/fedbabu/task.py

@@ -0,0 +1,115 @@
+"""fedbabu: A Flower / PyTorch app."""
+
+from collections import OrderedDict
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch.utils.data import DataLoader
+from torchvision.transforms import Compose, Normalize, ToTensor
+from flwr_datasets import FederatedDataset
+from flwr_datasets.partitioner import DirichletPartitioner
+from flwr_datasets.preprocessor import Merger
+
+
+class Net(nn.Module):
+    """Model (simple CNN adapted from 'PyTorch: A 60 Minute Blitz')"""
+
+    def __init__(self):
+        super(Net, self).__init__()
+        self.conv1 = nn.Conv2d(3, 6, 5)
+        self.pool = nn.MaxPool2d(2, 2)
+        self.conv2 = nn.Conv2d(6, 16, 5)
+        self.fc1 = nn.Linear(16 * 5 * 5, 120)
+        self.fc2 = nn.Linear(120, 84)
+        self.fc3 = nn.Linear(84, 10)
+
+    def forward(self, x):
+        x = self.pool(F.relu(self.conv1(x)))
+        x = self.pool(F.relu(self.conv2(x)))
+        x = x.view(-1, 16 * 5 * 5)
+        x = F.relu(self.fc1(x))
+        x = F.relu(self.fc2(x))
+        return self.fc3(x)
+
+
+fds = None  # Cache FederatedDataset
+
+
+def load_data(partition_id: int, num_partitions: int):
+    """Load partition CIFAR10 data."""
+    # Only initialize `FederatedDataset` once
+    global fds
+    if fds is None:
+        partitioner = DirichletPartitioner(
+            num_partitions=num_partitions, partition_by="label", alpha=0.5
+        )
+        fds = FederatedDataset(
+            dataset="uoft-cs/cifar10",
+            partitioners={"train": partitioner},
+            preprocessor=Merger({"train": ("train", "test")}),
+        )
+    partition = fds.load_partition(partition_id)
+    # Divide data on each node: 80% train, 20% test
+    partition_train_test = partition.train_test_split(test_size=0.2, seed=42)
+    pytorch_transforms = Compose(
+        [ToTensor(), Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]
+    )
+
+    def apply_transforms(batch):
+        """Apply transforms to the partition from FederatedDataset."""
+        batch["img"] = [pytorch_transforms(img) for img in batch["img"]]
+        return batch
+
+    partition_train_test = partition_train_test.with_transform(apply_transforms)
+    trainloader = DataLoader(partition_train_test["train"], batch_size=32, shuffle=True)
+    testloader = DataLoader(partition_train_test["test"], batch_size=32)
+    return trainloader, testloader
+
+
+def train(net, trainloader, epochs, device):
+    """Train the model on the training set."""
+    net.to(device)  # move model to GPU if available
+    criterion = torch.nn.CrossEntropyLoss().to(device)
+    optimizer = torch.optim.SGD(net.parameters(), lr=0.1, momentum=0.9)
+    net.train()
+    running_loss = 0.0
+    for _ in range(epochs):
+        for batch in trainloader:
+            images = batch["img"]
+            labels = batch["label"]
+            optimizer.zero_grad()
+            loss = criterion(net(images.to(device)), labels.to(device))
+            loss.backward()
+            optimizer.step()
+            running_loss += loss.item()
+
+    avg_trainloss = running_loss / len(trainloader)
+    return avg_trainloss
+
+
+def test(net, testloader, device):
+    """Validate the model on the test set."""
+    net.to(device)
+    criterion = torch.nn.CrossEntropyLoss()
+    correct, loss = 0, 0.0
+    with torch.no_grad():
+        for batch in testloader:
+            images = batch["img"].to(device)
+            labels = batch["label"].to(device)
+            outputs = net(images)
+            loss += criterion(outputs, labels).item()
+            correct += (torch.max(outputs.data, 1)[1] == labels).sum().item()
+    accuracy = correct / len(testloader.dataset)
+    loss = loss / len(testloader)
+    return loss, accuracy
+
+
+def get_weights(net):
+    return [val.cpu().numpy() for _, val in net.state_dict().items()]
+
+
+def set_weights(net, parameters):
+    params_dict = zip(net.state_dict().keys(), parameters)
+    state_dict = OrderedDict({k: torch.tensor(v) for k, v in params_dict})
+    net.load_state_dict(state_dict, strict=True)