PyTorch | 得到“RuntimeError: Found dtype Long but expected Float”

Question

I'm trying to train a CNN on a custom dataset. Code:

Dataset.py

class MyDataset(Dataset):
    def __init__(self, csv_file, root_dir):
        self.annotations = pd.read_csv(csv_file)
        self.root_dir = root_dir
        self.transform = transform

    def __len__(self):
        return len(self.annotations)

    def __getitem__(self, index):
        img_path = os.path.join(self.root_dir, self.annotations.iloc[index, 0])
        y_label = torch.tensor(int(self.annotations.iloc[index, 1]))
        img = cv2.imread(img_path)

        # resize
        res = cv2.resize(img, dsize=(50, 50), interpolation=cv2.INTER_CUBIC)
        
        # convert image to tensor
        res = torch.from_numpy(res)

        return (res, y_label)

Model.py

class ConvNet(torch.nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()

        f2 = 4
        self.layer2 = nn.Sequential(
            nn.Conv2d(50, f2, kernel_size=5, padding=2),
            nn.ReLU(),
            nn.BatchNorm2d(f2),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.fc1 = nn.Linear(100, 200)
        self.fc2 = nn.Linear(200, 20)
        self.fc3 = nn.Linear(20, 1)

    def forward(self, x):
        x = self.layer2(x.float())
        x = x.reshape(x.size(0), -1)
        x = self.fc1(x)
        x = self.fc2(x)
        x = self.fc3(x)
        return x

and here is my training code:

dataset = MyDataset(
    csv_file='dataset.csv',
    root_dir='tmp')

train_set, test_set = torch.utils.data.random_split(dataset, lengths=[500, 70])

train_loader = DataLoader(dataset=train_set, batch_size=16, shuffle=True)
test_loader = DataLoader(dataset=test_set, batch_size=16, shuffle=True)


model = ConvNet()
criterion = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.0001)

for epoch in range(20):
    losses = []

    for batch_idx, (data, targets) in enumerate(train_loader):

        data = data.to(device=device)
        targets = targets.to(device=device)

        # forward
        scores = model(data)
        loss = criterion(scores, targets)
        losses.append(loss.item())

        # backward
        optimizer.zero_grad()
        loss.backward()

        optimizer.step()

    print('Cost: {0} = {1}'.format(epoch, sum(losses)/len(losses)))

But I get RuntimeError: Found dtype Long but expected Float . This probably comes from the fact that I do x = self.layer2(x.float()) to avoid overflow.

I would like to know how to fix that error. It's difficult to pin-point where the exact problem comes from.

How can I solve this?

Answer 1

The problem might be caused by data tensor. When data loader calls images via getitem () method, image is read with opencv and transformed to tensor. I think at that point, type of your data tensor is long but it should be float. If you cast your numpy array -named res - to float it should work fine. You can see my solution below.

res = cv2.resize(img, dsize=(50, 50), interpolation=cv2.INTER_CUBIC)  
res = res.astype(np.float32) # you should add this line   
res = torch.from_numpy(res)
res = res.permute(2, 0, 1)