Question

我希望你们一切都好。我是PyTorch的新手，我遇到了一个在线代码，其中包含以下代码：

cuda = True if torch.cuda.is_available() else False
num_class = opt.num_class
num_repeats = opt.num_repeats
total=0
correct=0
acc=[]
acc1=[]
model = SHMnet(num_class)
# model = AlexNet1D(num_class)
learning_rate = opt.lr
print(model)
loss = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate,betas=(opt.b1,opt.b2))
if cuda:
    model=model.cuda()
    loss=loss.cuda()
FloatTensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor
LongTensor = torch.cuda.LongTensor if cuda else torch.LongTensor

traindataset = []
for label in range(num_class):
    epdataset = epDataset(label,num_repeats)
    traindataset = ConcatDataset([traindataset,epdataset])

testdataset =[]
for label in range(num_class):
    eptdataset = eptDataset(label,6)
    testdataset = ConcatDataset([testdataset,eptdataset])
dataloader = DataLoader(traindataset, batch_size=opt.batch_size)
viddataloader = DataLoader(testdataset,batch_size = opt.batch_size)
loss_r=[]
start = time.time()

for epoch in range(opt.n_epochs):
    print('Epoch: %d' % epoch)
    total = 0
    correct = 0
    total1 = 0
    correct1 = 0
    for i, (sdata, label) in enumerate(dataloader):
        batch_size = sdata.shape[0]
        sdata = Variable(sdata.type(FloatTensor))
       noise=Variable(torch.from_numpy(np.random.normal(1, 0.2, sdata.shape))).type(FloatTensor)
        x = torch.mul(sdata,noise).view(sdata.size(0), 1, sdata.size(1))
        print(x)
        print(x.size())
        label = Variable (label.type(LongTensor))
        print(label)
        optimizer.zero_grad()
        output = model(x)
        print(output)
        print(output.size())
        loss1 = loss(input=output, target=label)
        loss1.backward()
        optimizer.step()
        _, predicted = torch.max(model(x).data, 1)
        temp = (predicted == label).sum()
        correct += temp
        total += batch_size
        print(i, loss1.item())
        loss_r.append(loss1.item())
    print('Accuracy of training data is: %d %%' % (100 * correct / total))
    acc.append(100 * correct / total)

我设法找到一个数据集，但是，运行代码时出现以下错误：

RuntimeError: “dimension out of range (expected to be in range of [-1, 0], but got 1)”

因此，我不理解此错误。可能是什么原因以及如何解决？

批处理大小为60，类数为6

编辑1

输出和标签变量的输出是：

Labels:  tensor([0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5])
Labels Size/Shape:  torch.Size([12])
torch.Size([12, 512, 2])
Output:  tensor([0.0288, 0.0125, 0.0104, 0.0222, 0.0106, 0.0121],  grad_fn=<AddBackward0>)
Output Size/Shape:  torch.Size([6])

编辑2

我设法将批次大小更改为6，但是输出和标签变量的输出是：

Input Size/Shape:  torch.Size([6, 1, 2192])
Labels:  tensor([0, 1, 2, 3, 4, 5])
Labels Size/Shape:  torch.Size([6])
torch.Size([6, 512, 2])
Output:  tensor([ 0.0228, -0.0088,  0.0047,  0.0224,  0.0146,  0.0357], grad_fn=<AddBackward0>)
Output Size/Shape:  torch.Size([6])

但是，我遇到相同的错误，批处理大小为6，类数为6 谢谢

RuntimeError：“尺寸超出范围（预计在[-1，0]范围内，但得到1）”

0 个答案: