How to get dataset from prepare_data() to setup() in PyTorch Lightning

[Opss-0]

If my question does not meet the forum criteria, please remove it (as my question is related to Lightning)!

I made my own dataset using NumPy in the prepare_data() methods using the DataModules method of PyTorch Lightning. Now, I want to pass the data into the setup() method to split into training and validation.

import numpy as np 
import pytorch_lightning as pl 
from torch.utils.data import random_split, DataLoader, TensorDataset
import torch
from torch.autograd import Variable
from torchvision import transforms

np.random.seed(42)

device = 'cuda' if torch.cuda.is_available() else 'cpu'

class DataModuleClass(pl.LightningDataModule):
    def __init__(self):
        super().__init__()
        self.constant = 2
        self.batch_size = 10
        
    def prepare_data(self):
        a = np.random.uniform(0, 500, 500)
        b = np.random.normal(0, self.constant, len(a))

        c = a + b
        X = np.transpose(np.array([a, b]))
        
        # Converting numpy array to Tensor
        self.x_train_tensor = torch.from_numpy(X).float().to(device)
        self.y_train_tensor = torch.from_numpy(c).float().to(device)
        
        training_dataset = TensorDataset(self.x_train_tensor, self.y_train_tensor)

        return training_dataset
    
    def setup(self):
        data = # What I have to write to get the data from prepare_data()
        self.train_data, self.val_data = random_split(data, [400, 100])
        
        
    def train_dataloader(self):
        training_dataloader = setup() # Need to get the training data
        return DataLoader(self.train_data)

    def val_dataloader(self):
        return DataLoader(self.val_data)
    
obj = DataModuleClass()
print(obj.prepare_data())

[mostafiz67]

def prepare_data(self):
    a = np.random.uniform(0, 500, 500)
    b = np.random.normal(0, self.constant, len(a))

    c = a + b
    X = np.transpose(np.array([a, b]))

    # Converting numpy array to Tensor
    self.x_train_tensor = torch.from_numpy(X).float().to(device)
    self.y_train_tensor = torch.from_numpy(c).float().to(device)
    
    training_dataset = TensorDataset(self.x_train_tensor, self.y_train_tensor)

    self.training_dataset = training_dataset

def setup(self):
    data = self.training_dataset
    self.train_data, self.val_data = random_split(data, [400, 100])
    
    
def train_dataloader(self):
    return DataLoader(self.train_data)

def val_dataloader(self):
    return DataLoader(self.val_data)