即使使用GPU，训练也无法加快速度

如何解决即使使用GPU，训练也无法加快速度

transform = transforms.Compose([transforms.Resize(IMG_SIZE),transforms.CenterCrop(CROP_SIZE),transforms.ToTensor()]) 

class LandmarksDatasetTrain(Dataset):
    """Landmarks dataset.""" 

    def __init__(self,landmarks_frame,root_dir,transform=None):
        """
        Args:
            csv_file (string): Path to the csv file with annotations.
            root_dir (string): Directory with all the images.
            transform (callable,optional): Optional transform to be applied
                on a sample.
        """
        self.landmarks_frame = landmarks_frame
        self.root_dir = root_dir
        self.transform = transform 

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

    def __getitem__(self,idx):
        if torch.is_tensor(idx):
            idx = idx.tolist()
        img_name = os.path.join(self.root_dir,self.landmarks_frame.loc[idx,'id'][0],'id'][1],'id'][2],'id'])
        img_name += ".jpg"
        image = Image.open(img_name)
        landmarks = self.landmarks_frame.loc[idx,'landmark_id']
        sample = {'image': image,'landmarks': landmarks}

        if self.transform:
            sample['image'] = self.transform(sample['image'])
            sample['landmarks'] = torch.tensor(sample['landmarks'])

        return sample

dataset_train = LandmarksDatasetTrain(landmarks_frame = frame,root_dir='/kaggle/input/landmark-recognition-2020/train',transform=transform)

train_loader = DataLoader(dataset_train,batch_size=4,shuffle=True,num_workers=4,drop_last=False)

class Net(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(CROP_SIZE*CROP_SIZE*3,64)
        self.fc2 = nn.Linear(64,64)
        self.fc3 = nn.Linear(64,64)
        self.fc4 = nn.Linear(64,frame['landmark_id'].nunique())

    def forward(self,x):
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = F.relu(self.fc3(x))
        x = self.fc4(x)
        return F.log_softmax(x,dim=1)

net = Net()
net.to(device)

for epoch in range(3): 
    optimizer = optim.Adam(net.parameters(),lr=0.001)
    for data in tqdm(train_loader):  
        X = data['image'].to(device)  
        y = data['landmarks'].to(device) 
        net.zero_grad()  
        output = net(X.view(-1,CROP_SIZE*CROP_SIZE*3))  
        loss = F.nll_loss(output,y) 
        loss.backward()  
        optimizer.step() 
    print(loss)  

批量为4

data ['image']和data ['landmarks']是张量device = torch.device（“ cuda：0”），而我正在使用的深度学习库是Pytorch，但GPU仍然对我不起作用。其用法显示为5％，总时间为1到3.5到4个小时

如果有人指出我的错误，将会非常有帮助。

附加资源使用情况和GPU配置的图像。

附加图像以显示GPU已开启

这是我笔记本的链接 https://www.kaggle.com/hiteshsom/google-landmark-recognition