RuntimeError：cuda运行时错误（710）：设备端断言触发于

Question

使用 pytorch 训练图像分类
出现以下错误消息K

---

RuntimeError Traceback（最近一次调用最后一次） in 29 print(len(train_loader.dataset),len(valid_loader.dataset)) 30 #break ---> 31 train_loss, train_acc ,model= train(model, device, train_loader, optimizationr,标准）32 valid_loss，valid_acc，模型=评估（模型，设备，valid_loader，标准）33

in train(model, device, iterator, optimizationr, criteria) 21 acc =calculate_accuracy(fx, y) 22 #print("5.") ---> 23 loss.backward() 24 25 optimizationr.step()

~/venv/lib/python3.7/site-packages/torch/tensor.py 向后（self，gradient，retain_graph，create_graph）164个产品。默认为False. 第165章 166章 166章 167章

〜/venv/lib/python3.7/site-packages/torch/autograd/ init .py 向后（张量，grad_tensors，retain_graph，create_graph，grad_variables） 97 Variable._execution_engine.run_backward（ 98 张量，grad_tensors，retain_graph，create_graph， ---> 99allow_unreachable=True) #allow_unreachable 标志 100 101

RuntimeError：cuda 运行时错误 (710)：在 /pytorch/aten/src/THC/generic/THCTensorMath.cu:26 触发设备端断言

相关代码块在这里

def train(model, device, iterator, optimizer, criterion):

print('train')
epoch_loss = 0
epoch_acc = 0

model.train()


for (x, y) in iterator:
    #print(x,y)
    x,y = x.cuda(), y.cuda()
    #x = x.to(device)
    #y = y.to(device)
    #print('1')
    optimizer.zero_grad()
    #print('2')
    fx = model(x)
    #print('3')
    loss = criterion(fx, y)
    #print("4.loss->",loss)
    acc = calculate_accuracy(fx, y)
    #print("5.")
    loss.backward()

    optimizer.step()

    epoch_loss += loss.item()
    epoch_acc += acc.item()

return epoch_loss / len(iterator), epoch_acc / len(iterator),model


    EPOCHS = 5
    SAVE_DIR = 'models'
    MODEL_SAVE_PATH = os.path.join(SAVE_DIR, 'please.pt')
    from torch.utils.data import DataLoader
    best_valid_loss = float('inf')

    if not os.path.isdir(f'{SAVE_DIR}'):
        os.makedirs(f'{SAVE_DIR}')
    print("start")
    for epoch in range(EPOCHS):
        print('================================',epoch ,'================================')
        for i , (train_idx, valid_idx) in enumerate(zip(train_indexes, valid_indexes)):
            print(i,train_idx,valid_idx,len(train_idx),len(valid_idx))

            traindf = df_train.iloc[train_index, :].reset_index()
            validdf = df_train.iloc[valid_index, :].reset_index()

            #traindf = df_train
            #validdf = df_train

            train_dataset = TrainDataset(traindf, mode='train', transforms=data_transforms)
            valid_dataset = TrainDataset(validdf, mode='valid', transforms=data_transforms)

            train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
            valid_loader = DataLoader(valid_dataset, batch_size=batch_size, shuffle=False)



            print(len(train_loader.dataset),len(valid_loader.dataset))
            #break
            train_loss, train_acc ,model= train(model, device, train_loader, optimizer, criterion)
            valid_loss, valid_acc,model = evaluate(model, device, valid_loader, criterion)

            if valid_loss < best_valid_loss:
                best_valid_loss = valid_loss
                torch.save(model,MODEL_SAVE_PATH)

            print(f'| Epoch: {epoch+1:02} | Train Loss: {train_loss:.3f} | Train Acc: {train_acc*100:05.2f}% | Val. Loss: {valid_loss:.3f} | Val. Acc: {valid_acc*100:05.2f}% |')

分割 = zip(train_indexes, valid_indexes) [ 3692 3696 3703 ... 30733 30734 30735] [ 0 1 2 ... 4028 4041 4046] [ 0 1 2 ... 30733 30734 30735] [3692 3696 3703 ... 7986 7991 8005] [ 0 1 2 ... 30733 30734 30735] [ 7499 7500 7502 ... 11856 11858 11860] [ 0 1 2 ... 30733 30734 30735] [11239 11274 11280 ... 15711 15 716 15720] [0 1 2 ... 30733 30734 30735] [15045 15051 15053 ... 19448 19460 19474] [
0 1 2 ... 30733 30734 30735] [18919 18920 18926 ... 23392 23400 23402] [ 0 1 2 ... 30733 30734 30735 ] [22831 22835 22846 ... 27118 27120 27124] [ 0 1 2 ... 27118 27120 27124] [26718 26721 26728 ... 30733 30734 30735]

Answer 1

你的损失函数是多少？

我也遇到这个错误。我的问题是multi-class分类，我正在使用crossEntropy损失。

正如文档中所说，标签应该在类数的范围[0, C-1]内。C但我的标签不在范围内，当我为标签使用正确的值时，一切都很好。