python - 预期的设备 cuda:0 但在我已经将设备分配为 cuda 时在 PyTorch 中获得了设备 cpu
问题描述
我有以下神经网络代码，我得到“预期设备 cuda：0 但在 PyTorch 中得到设备 cpu”错误，我不知道为什么。我将设备指定为 cuda，打印行返回 cuda。我已经尝试将设备分配为 device = cuda:0 以防万一，但这没有效果。这是代码：
def run():
torch.multiprocessing.freeze_support()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
metabolites = pd.read_excel("testmetabolitedata.xlsx")
subject_metadata = pd.read_excel("testsubj.xlsx")
metabolitesdf = pd.DataFrame(data=metabolites)
metabolitesdf = metabolitesdf.iloc[:, 1:9153]
subjectsdf = pd.DataFrame(data=subject_metadata)
n_samples, n_metabolites = metabolitesdf.shape
print(n_samples)
#genotypes of the target gene
print(subjectsdf['SLCO1B1_rs4149056'])
genotypes = subjectsdf['SLCO1B1_rs4149056']
print(genotypes)
# print('{} unique genotypes'.format(len(set(genotypes))))
labels = [1 if g == 1 else 0 for g in genotypes]
print('{} samples with genotype 1 out of {} samples ({:.1%})'.format(sum(labels), len(labels),
sum(labels) / len(labels)))
#Insert 0 into index 0 (first) into the list for the first row with column names
labels.insert(0, 0)
#log transform
log_metabol = np.log10(metabolitesdf + 1)
#Split data into training and validation 70% / 30%
data = torch.utils.data.TensorDataset(torch.Tensor(np.array(log_metabol)),
torch.Tensor(labels))
train, val = torch.utils.data.random_split(data, [int(0.7 * len(data)),
len(data) - int(0.7 * len(data))])
print('{:.0f}/{} training/total ({:.1%}) in training set, {:.0f}/{} val/total ({:.1%}) in validation set'.format(\
train[:][1].sum(), len(train), train[:][1].sum() / len(train),
val[:][1].sum(), len(val), val[:][1].sum() / len(val)))
class MultiLayerPredictor(torch.nn.Module):
def __init__(self, input_shape, output_shape=1, hidden_dim=1024, **kwargs):
super().__init__()
self.fc1 = torch.nn.Linear(in_features=input_shape, out_features=hidden_dim)
self.bn1 = torch.nn.BatchNorm1d(hidden_dim)
self.fc2 = torch.nn.Linear(in_features=hidden_dim, out_features=hidden_dim)
self.bn2 = torch.nn.BatchNorm1d(hidden_dim)
self.fc3 = torch.nn.Linear(in_features=hidden_dim, out_features=output_shape)
def forward(self, x):
l1 = torch.relu(self.bn1(self.fc1(x)))
l2 = torch.relu(self.bn2(self.fc2(l1)))
return torch.sigmoid(self.fc3(l2)).reshape(-1)
#load the training and validation sets
print("Load training and validation data ")
train_loader = torch.utils.data.DataLoader(train, batch_size=128,
shuffle=True, num_workers=10, pin_memory=True)
val_loader = torch.utils.data.DataLoader(val, batch_size=128,
shuffle=False, num_workers=10, pin_memory=True)
print("Loading complete, create model")
model3 = MultiLayerPredictor(input_shape=n_metabolites).to(device)
print("Model created! Moving to optimizer")
optimizer3 = torch.optim.SGD(model3.parameters(), lr=1e-2)
print("Optimizer done")
objective3 = torch.nn.BCELoss()
epochs = 30
print_stats_interval = 10
log3 = []
print("Moving to training loop")
for epoch in range(epochs):
loss = n_correct = 0
model3.train()
for batch, target in train_loader:
batch = batch.view(-1, n_metabolites).to(device)
optimizer3.zero_grad()
outputs = model3(batch) # stack trace shows the issue being either on this line
train_loss = objective3(outputs, target) # or this line
loss += train_loss.item()
n_correct += (target == (outputs.reshape(-1) > 0.5).float()).sum()
train_loss.backward()
optimizer3.step()
loss = loss / len(train_loader)
acc = (n_correct.float() / len(train)).numpy()
epoch += 1
model3.eval();
val_loss = val_n_correct = 0
with torch.no_grad():
for batch, target in val_loader:
batch = batch.view(-1, n_metabolites).to(device)
outputs = model3(batch)
val_loss += objective3(outputs, target)
val_n_correct += (target == (outputs.reshape(-1) > 0.5).float()).sum()
val_loss = (val_loss / len(val_loader)).numpy()
val_acc = (val_n_correct.float() / len(val)).numpy()
if (epoch % print_stats_interval) == 0 or epoch == epochs:
print(f'epoch={epoch:.0f}, loss={loss:.5f}, val_loss={np.round(val_loss,5):.5f}, acc={np.round(acc,5):.5f}, val_acc={np.round(val_acc,5):.5f}')
log3.append((epoch, loss, val_loss, acc, val_acc))
log3 = pd.DataFrame(log3, columns=['epoch', 'loss', 'val_loss', 'acc', 'val_acc'])
plt.figure(figsize=(6, 3))
plt.plot(log3['epoch'], log3['loss'], label='Training');
plt.plot(log3['epoch'], log3['val_loss'], label='Validation');
plt.xlabel('Epoch'); plt.ylabel('Loss')
plt.legend();
val_log_mutations = val_hcc[:][0].numpy().reshape(-1)
val_true_labels = val_hcc[:][1].numpy() + 0
res = model3(val_hcc[:][0])
predictions = (res.detach().numpy().reshape(-1) > 0.5) + 0
correct = (val_true_labels == predictions) + 0
n_correct = correct.sum()
print('{}/{} ({:.1%}) in the validation set'.format(n_correct, len(correct), n_correct / len(correct)))
print('Majority classifier accuracy: {:.1%}'.format((len(correct) - val_true_labels.sum()) / len(correct)))
if __name__ == '__main__':
run()
这里发生了什么？这里的堆栈跟踪：
Traceback (most recent call last):
File "//ad..fi/home/h/h/Desktop/neuralnet/neuralnet_train.py", line 142, in <module>
run()
File "//ad..fi/home/h/h/Desktop/neuralnet/neuralnet_train.py", line 99, in run
train_loss = objective3(outputs, target)
File "C:\Users\h\AppData\Roaming\Python\Python38\site-packages\torch\nn\modules\module.py", line 550, in __call__
result = self.forward(*input, **kwargs)
File "C:\Users\h\AppData\Roaming\Python\Python38\site-packages\torch\nn\modules\loss.py", line 516, in forward
return F.binary_cross_entropy(input, target, weight=self.weight, reduction=self.reduction)
File "C:\Users\h\AppData\Roaming\Python\Python38\site-packages\torch\nn\functional.py", line 2378, in binary_cross_entropy
return torch._C._nn.binary_cross_entropy(
RuntimeError: expected device cuda:0 but got device cpu
PS Microsoft.PowerShell.Core\FileSystem::\\ad..fi\home\h\h\Desktop\neuralnet>
解决方案
在循环的训练和验证中也将目标移动到 CUDA。
for batch, target in train_loader:
batch,target = batch.view(-1, n_metabolites).to(device),target.to(device)
.
.
.
for batch, target in val_loader:
batch,target = batch.view(-1, n_metabolites).to(device),target.to(device)``
.
.
.