RuntimeError:输入类型(torch.FloatTensor)和权重类型(torch.cuda.FloatTensor)应该是一样的 [英] RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same

问题描述

我正在尝试按如下方式训练以下 CNN，但我不断收到关于 .cuda() 的相同错误，我不知道如何修复它.到目前为止，这是我的一段代码.

I am trying to train the following CNN as follows, but I keep getting the same error regarding .cuda() and I am not sure how to fix it. Here is a chunk of my code so far.

import matplotlib.pyplot as plt
import numpy as np
import torch
from torch import nn
from torch import optim
import torch.nn.functional as F
import torchvision
from torchvision import datasets, transforms, models
from torch.utils.data.sampler import SubsetRandomSampler


data_dir = "/home/ubuntu/ML2/ExamII/train2/"
valid_size = .2

# Normalize the test and train sets with torchvision
train_transforms = transforms.Compose([transforms.Resize(224),
                                           transforms.ToTensor(),
                                           ])

test_transforms = transforms.Compose([transforms.Resize(224),
                                          transforms.ToTensor(),
                                          ])

# ImageFolder class to load the train and test images
train_data = datasets.ImageFolder(data_dir, transform=train_transforms)
test_data = datasets.ImageFolder(data_dir, transform=test_transforms)


# Number of train images
num_train = len(train_data)
indices = list(range(num_train))
# Split = 20% of train images
split = int(np.floor(valid_size * num_train))
# Shuffle indices of train images
np.random.shuffle(indices)
# Subset indices for test and train
train_idx, test_idx = indices[split:], indices[:split]
# Samples elements randomly from a given list of indices
train_sampler = SubsetRandomSampler(train_idx)
test_sampler = SubsetRandomSampler(test_idx)
# Batch and load the images
trainloader = torch.utils.data.DataLoader(train_data, sampler=train_sampler, batch_size=1)
testloader = torch.utils.data.DataLoader(test_data, sampler=test_sampler, batch_size=1)


#print(trainloader.dataset.classes)

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

model.fc = nn.Sequential(nn.Linear(2048, 512),
                                 nn.ReLU(),
                                 nn.Dropout(0.2),
                                 nn.Linear(512, 10),
                                 nn.LogSigmoid())
                                 # nn.LogSoftmax(dim=1))
# criterion = nn.NLLLoss()
criterion = nn.BCELoss()
optimizer = optim.Adam(model.fc.parameters(), lr=0.003)
model.to(device)

#Train the network
for epoch in range(2):  # loop over the dataset multiple times

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 2000 == 1999:    # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')

但是，我一直在控制台中收到此错误:

However, I keep getting this error in the console:

RuntimeError: 输入类型(torch.FloatTensor)和权重类型(torch.cuda.FloatTensor)应该是一样的`

RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same`

关于如何修复它的任何想法?我读到可能模型没有被推入我的 GPU，但不知道如何修复它.谢谢！

Any thoughts on how to fix it? I read that maybe the model hasn't been pushed into my GPU, but not sure how to fix it. Thanks!

推荐答案

您收到此错误是因为您的模型在 GPU 上，但您的数据在 CPU 上.因此，您需要将输入张量发送到 GPU.

You get this error because your model is on the GPU, but your data is on the CPU. So, you need to send your input tensors to the GPU.

inputs, labels = data                         # this is what you had
inputs, labels = inputs.cuda(), labels.cuda() # add this line

或者像这样，与您的其余代码保持一致:

Or like this, to stay consistent with the rest of your code:

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

inputs, labels = inputs.to(device), labels.to(device)

如果您的输入张量在 GPU 上但您的模型权重不在 GPU 上，则会引发 相同的错误.在这种情况下，您需要将模型权重发送到 GPU.

The same error will be raised if your input tensors are on the GPU but your model weights aren't. In this case, you need to send your model weights to the GPU.

model = MyModel()

if torch.cuda.is_available():
    model.cuda()

这里是 cuda() 和 cpu()，相反.

Here is the documentation for cuda() and cpu(), its opposite.

这篇关于RuntimeError:输入类型(torch.FloatTensor)和权重类型(torch.cuda.FloatTensor)应该是一样的的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！