pytorch create your dataset

class CustomDataset(Dataset):
    def __int__(self,data,targets):
        self.data=data
        self.target=targets
    def __len__(self):
        return len(self.data)
    def __getitem__(self,index):
        x=self.data[index]
        y=self.target[index]
        return x,y

if torch.cuda.is_available():
    print("GPU is available")
else:
    print("GPU is not available")
    

#get x,y
data=[...] #your data x
targets=[...] #your targets y

custom_dataset=CustomDataset(data,targets)
#dataloader=torch.utils.data.DataLoader(custom_dataset,batch_size=64,shuffle=True)

# 将数据集分割成训练集和测试集
train_ratio=0.8
train_size = int(len(custom_dataset) * train_ratio)
test_size = len(custom_dataset) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(custom_dataset, [train_size, test_size])

# 创建训练集和测试集的数据加载器
batch_size = 4#32
trainloader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
testloader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)