如何为自定义数据集类预处理 Pytorch 中的数据？

Question

I am new to PyTorch, and I have a dataset given in a pickle file format, with the Dataset class already defined (which I'm not allowed to make changes to). The code for the Dataset class is as follows:

class MyData(Dataset):
    def __init__(self, mode):
        with open(mode+'.pkl', 'rb') as handle:
            data = pickle.load(handle)
            self.X = data['x'].astype('float')
            self.y = data['y'].astype('long')

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

    def __getitem__(self, idx):
        if torch.is_tensor(idx):
            idx = idx.tolist()

        sample = (self.X[idx], self.y[idx])

        return sample

The returned data is not normalized, and I was looking at how to do that in PyTorch, but most of them were using the transform method which I think I cannot use because I'm not allowed to change the Dataset class.

How do I prepare the data before feeding it to the neural network through the DataLoader class?