forked from NVIDIA/NVFlare
-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
add client executor launcher; upgrade flwr scripts to 1.7.0 versions
- Loading branch information
1 parent
6434435
commit a2bb01a
Showing
6 changed files
with
476 additions
and
264 deletions.
There are no files selected for viewing
379 changes: 237 additions & 142 deletions
379
examples/advanced/flower/fedprox/flower_fedprox.ipynb
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
173 changes: 108 additions & 65 deletions
173
examples/advanced/flower/fedprox/jobs/flwr_cifar10/app/custom/client.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,98 +1,141 @@ | ||
| from collections import OrderedDict | ||
| import argparse | ||
| import warnings | ||
| from collections import OrderedDict | ||
|
|
||
| import flwr as fl | ||
| from flwr_datasets import FederatedDataset | ||
| import numpy as np | ||
| import torch | ||
| import torch.nn as nn | ||
| import torch.nn.functional as F | ||
| from torchvision.transforms import Compose, ToTensor, Normalize | ||
| from torch.utils.data import DataLoader | ||
| from torchvision.datasets import CIFAR10 | ||
| from torchvision.transforms import Compose, Normalize, ToTensor | ||
| from tqdm import tqdm | ||
|
|
||
|
|
||
| # ############################################################################# | ||
| # Regular PyTorch pipeline: nn.Module, train, test, and DataLoader | ||
| # 1. Regular PyTorch pipeline: nn.Module, train, test, and DataLoader | ||
| # ############################################################################# | ||
|
|
||
| warnings.filterwarnings("ignore", category=UserWarning) | ||
| DEVICE = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") | ||
|
|
||
|
|
||
| class Net(nn.Module): | ||
| """Model (simple CNN adapted from 'PyTorch: A 60 Minute Blitz')""" | ||
|
|
||
| def __init__(self) -> None: | ||
| 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: torch.Tensor) -> torch.Tensor: | ||
| 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) | ||
| """Model (simple CNN adapted from 'PyTorch: A 60 Minute Blitz')""" | ||
|
|
||
| def __init__(self) -> None: | ||
| 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: torch.Tensor) -> torch.Tensor: | ||
| 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) | ||
|
|
||
|
|
||
| def train(net, trainloader, epochs): | ||
| """Train the model on the training set.""" | ||
| criterion = torch.nn.CrossEntropyLoss() | ||
| optimizer = torch.optim.SGD(net.parameters(), lr=0.001, momentum=0.9) | ||
| for _ in range(epochs): | ||
| for images, labels in trainloader: | ||
| print("train...") | ||
| optimizer.zero_grad() | ||
| criterion(net(images.to(DEVICE)), labels.to(DEVICE)).backward() | ||
| optimizer.step() | ||
| """Train the model on the training set.""" | ||
| criterion = torch.nn.CrossEntropyLoss() | ||
| optimizer = torch.optim.SGD(net.parameters(), lr=0.001, momentum=0.9) | ||
| for _ in range(epochs): | ||
| for batch in tqdm(trainloader, "Training"): | ||
| images = batch["img"] | ||
| labels = batch["label"] | ||
| optimizer.zero_grad() | ||
| criterion(net(images.to(DEVICE)), labels.to(DEVICE)).backward() | ||
| optimizer.step() | ||
|
|
||
|
|
||
| def test(net, testloader): | ||
| """Validate the model on the test set.""" | ||
| criterion = torch.nn.CrossEntropyLoss() | ||
| correct, total, loss = 0, 0, 0.0 | ||
| with torch.no_grad(): | ||
| for images, labels in testloader: | ||
| outputs = net(images.to(DEVICE)) | ||
| loss += criterion(outputs, labels.to(DEVICE)).item() | ||
| total += labels.size(0) | ||
| correct += (torch.max(outputs.data, 1)[1] == labels).sum().item() | ||
| return loss / len(testloader.dataset), correct / total | ||
|
|
||
| def load_data(): | ||
| """Load CIFAR-10 (training and test set).""" | ||
| trf = Compose([ToTensor(), Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]) | ||
| trainset = CIFAR10("./data", train=True, download=True, transform=trf) | ||
| testset = CIFAR10("./data", train=False, download=True, transform=trf) | ||
| return DataLoader(trainset, batch_size=32, shuffle=True), DataLoader(testset) | ||
| """Validate the model on the test set.""" | ||
| criterion = torch.nn.CrossEntropyLoss() | ||
| correct, loss = 0, 0.0 | ||
| with torch.no_grad(): | ||
| for batch in tqdm(testloader, "Testing"): | ||
| 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) | ||
| return loss, accuracy | ||
|
|
||
|
|
||
| def load_data(node_id): | ||
| """Load partition CIFAR10 data.""" | ||
| fds = FederatedDataset(dataset="cifar10", partitioners={"train": 3}) | ||
| partition = fds.load_partition(node_id) | ||
| # Divide data on each node: 80% train, 20% test | ||
| partition_train_test = partition.train_test_split(test_size=0.2) | ||
| 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 | ||
|
|
||
|
|
||
| # ############################################################################# | ||
| # Federating the pipeline with Flower | ||
| # 2. Federation of the pipeline with Flower | ||
| # ############################################################################# | ||
|
|
||
| # Get node id | ||
| #parser = argparse.ArgumentParser(description="Flower") | ||
| #parser.add_argument( | ||
| # "--node-id", | ||
| # choices=[0, 1, 2], | ||
| # required=True, | ||
| # type=int, | ||
| # help="Partition of the dataset divided into 3 iid partitions created artificially.", | ||
| #) | ||
| #node_id = parser.parse_args().node_id | ||
| node_id = np.random.randint(0,3) | ||
| print(f"START FLOWER CLIENT [node_id={node_id}]") | ||
|
|
||
| # Load model and data (simple CNN, CIFAR-10) | ||
| net = Net().to(DEVICE) | ||
| trainloader, testloader = load_data() | ||
| trainloader, testloader = load_data(node_id=node_id) | ||
|
|
||
|
|
||
| # Define Flower client | ||
| class FlowerClient(fl.client.NumPyClient): | ||
| def get_parameters(self, config): | ||
| return [val.cpu().numpy() for _, val in net.state_dict().items()] | ||
| def get_parameters(self, config): | ||
| return [val.cpu().numpy() for _, val in net.state_dict().items()] | ||
|
|
||
| def set_parameters(self, 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) | ||
|
|
||
| def set_parameters(self, 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) | ||
| def fit(self, parameters, config): | ||
| self.set_parameters(parameters) | ||
| train(net, trainloader, epochs=1) | ||
| return self.get_parameters(config={}), len(trainloader.dataset), {} | ||
|
|
||
| def fit(self, parameters, config): | ||
| self.set_parameters(parameters) | ||
| train(net, trainloader, epochs=1) | ||
| return self.get_parameters(config={}), len(trainloader.dataset), {} | ||
| def evaluate(self, parameters, config): | ||
| self.set_parameters(parameters) | ||
| loss, accuracy = test(net, testloader) | ||
| return loss, len(testloader.dataset), {"accuracy": accuracy} | ||
|
|
||
| def evaluate(self, parameters, config): | ||
| self.set_parameters(parameters) | ||
| loss, accuracy = test(net, testloader) | ||
| return float(loss), len(testloader.dataset), {"accuracy": float(accuracy)} | ||
|
|
||
| # Start Flower client | ||
| fl.client.start_numpy_client(server_address="0.0.0.0:8080", client=FlowerClient(), insecure=True) # "127.0.0.1:8080" | ||
| fl.client.start_client( | ||
| server_address="127.0.0.1:8080", | ||
| client=FlowerClient().to_client(), | ||
| ) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.