Question

我是pytorch的新手，正在使用ResNet50模型进行训练。

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = models.resnet50(pretrained=True)

for param in model.parameters():
    param.requires_grad = False

model.fc = nn.Sequential(nn.Linear(2048, 512),nn.ReLU(),nn.Dropout(0.2),nn.Linear(512, 10),nn.LogSoftmax(dim=1))
criterion = nn.NLLLoss()

optimizer = optim.Adam(model.fc.parameters(), lr=0.003)
model.to(device)


epochs = 1
steps = 0
running_loss = 0
print_every = 10
train_losses, test_losses = [], []
for epoch in range(epochs):
    for inputs, labels in trainloader:
        steps += 1
        inputs, labels = inputs.to(device), labels.to(device)
        optimizer.zero_grad()

        logps = model.forward(inputs)
        loss = criterion(logps, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()

        if steps % print_every == 0:
            test_loss = 0
            accuracy = 0
            model.eval()
            with torch.no_grad():
                for inputs, labels in testloader:
                    inputs, labels = inputs.to(device),labels.to(device)
                    logps = model.forward(inputs)
                    batch_loss = criterion(logps, labels)
                    test_loss += batch_loss.item()

                    ps = torch.exp(logps)
                    top_p, top_class = ps.topk(1, dim=1)
                    equals = top_class == labels.view(*top_class.shape)
                    accuracy += torch.mean(equals.type(torch.FloatTensor)).item()
            train_losses.append(running_loss/len(trainloader))
            test_losses.append(test_loss/len(testloader))                    
            print(f"Epoch {epoch+1}/{epochs}.. "
                  f"Train loss: {running_loss/print_every:.3f}.. "
                  f"Test loss: {test_loss/len(testloader):.3f}.. "
                  f"Test accuracy: {accuracy/len(testloader):.3f}")
            running_loss = 0
            model.train()

此代码在Google合作实验室工作正常，但在我的本地计算机（CPU）上执行“ model.forward（inputs）”时，出现错误“非法指令核心转储”。我尝试更新pytorch版本，但问题仍然存在。

Answer 1

请尝试：CPU：＃-GPU（例如：0）

示例

import torch
import torch
import pycuda.driver as cuda
cuda.init()
torch.cuda.is_available()
# True
## Get Id of default device
torch.cuda.current_device()
# 0
cuda.Device(0).name() # '0' is the id of your GPU
# Tesla K80

资料来源：完整参考 https://medium.com/p/speed-up-your-algorithms-part-1-pytorch-56d8a4ae7051

Pytorch：加载ResNet50模型时转储了非法指令核心

1 个答案:

示例