RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _th_set_ #3902
Description
RuntimeError when adding Batchnorm in the tutorial
differ from
#2498
#2132
I got a new problem:
Traceback (most recent call last):
File "/home/ubuntu/liangenmin/Project/PySyft-master/mytest.py", line 117, in
train(args, model, device, federated_train_loader, optimizer, epoch)
File "/home/ubuntu/liangenmin/Project/PySyft-master/mytest.py", line 84, in train
model.get() # <-- NEW: get the model back
File "/home/ubuntu/liangenmin/Project/PySyft-master/syft/frameworks/torch/hook/hook.py", line 671, in module_get_
p.get_()
File "/home/ubuntu/liangenmin/Project/PySyft-master/syft/frameworks/torch/tensors/interpreters/native.py", line 687, in get_
return self.get(*args, inplace=True, **kwargs)
File "/home/ubuntu/liangenmin/Project/PySyft-master/syft/frameworks/torch/tensors/interpreters/native.py", line 674, in get
self.set_(tensor)
RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to th_set
Process finished with exit code 1
Something wrong when model.get(), if I delete "to(device)", it works when I use cpu for data and model. It seems that type doesn't change in BN.
Here is my code:
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
import syft as sy # <-- NEW: import the Pysyft library
epochs = 10
hook = sy.TorchHook(torch) # <-- NEW: hook PyTorch ie add extra functionalities to support Federated Learning
bob = sy.VirtualWorker(hook, id="bob") # <-- NEW: define remote worker bob
alice = sy.VirtualWorker(hook, id="alice")
class Arguments():
def __init__(self):
self.batch_size = 64
self.test_batch_size = 1000
self.epochs = epochs
self.lr = 0.01
self.momentum = 0.5
self.no_cuda = False
self.seed = 1
self.log_interval = 30
self.save_model = False
args = Arguments()
use_cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
device = torch.device("cuda" if use_cuda else "cpu")
kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
federated_train_loader = sy.FederatedDataLoader( # <-- this is now a FederatedDataLoader
datasets.MNIST('../data', train=True, download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
]))
.federate((bob, alice)), # <-- NEW: we distribute the dataset across all the workers, it's now a FederatedDataset
batch_size=args.batch_size, shuffle=True, **kwargs)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.test_batch_size, shuffle=True, **kwargs)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 20, 5, 1)
self.conv2 = nn.Conv2d(20, 50, 5, 1)
self.fc1 = nn.Linear(4*4*50, 500)
self.fc2 = nn.Linear(500, 10)
self.bn1 = nn.BatchNorm2d(20)
def forward(self, x):
x = F.relu(self.conv1(x))
x = self.bn1(x)
x = F.max_pool2d(x, 2, 2)
x = F.relu(self.conv2(x))
x = F.max_pool2d(x, 2, 2)
x = x.view(-1, 4*4*50)
x = F.relu(self.fc1(x))
x = self.fc2(x)
return F.log_softmax(x, dim=1)
def train(args, model, device, federated_train_loader, optimizer, epoch):
model.train()
for batch_idx, (data, target) in enumerate(federated_train_loader): # <-- now it is a distributed dataset
model.send(data.location) # <-- NEW: send the model to the right location
data, target = data.to(device), target.to(device)
# data, target = data.cuda(), target.cuda()
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
loss.backward()
optimizer.step()
model.get() # <-- NEW: get the model back
if batch_idx % args.log_interval == 0:
loss = loss.get() # <-- NEW: get the loss back
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * args.batch_size, len(federated_train_loader) * args.batch_size,
100. * batch_idx / len(federated_train_loader), loss.item()))
def test(args, model, device, test_loader):
model.eval()
test_loss = 0
correct = 0
with torch.no_grad():
for data, target in test_loader:
data, target = data.to(device), target.to(device)
output = model(data)
test_loss += F.nll_loss(output, target, reduction='sum').item() # sum up batch loss
pred = output.argmax(1, keepdim=True) # get the index of the max log-probability
correct += pred.eq(target.view_as(pred)).sum().item()
test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
model = Net().to(device)
optimizer = optim.SGD(model.parameters(), lr=args.lr) # TODO momentum is not supported at the moment
for epoch in range(1, args.epochs + 1):
train(args, model, device, federated_train_loader, optimizer, epoch)
test(args, model, device, test_loader)
if (args.save_model):
torch.save(model.state_dict(), "mnist_cnn.pt")
python 3.7.7
torch 1.4.0