$.$ Download the MNIST dataset and make a custom dataloader using torch.utils.data.Dataset, DataLoader.

Compare the loading performance of your scratch implemented data loader with the one provided by PyTorch

across different batch sizes $(128,256,512,1024).$ Plot a graph illustrating the relationship between batch size

and loading time.

$2.$Implement a Feed$-$Forward neural network architecture from scratch featuring four hidden layers, each comprising

minimum $32$ neurons $($excluding input and output layers$).$ Train the model using the most effective data loader

identified in the previous question with ReLU activation function. Employ the Cross$-$Entropy loss function

and opt for the Stochastic Gradient Descent $($SGD$)$ optimizer with default parameters, setting the learning

rate to $0\mathrm{.}0003.$ Plot graphs depicting the loss and accuracy during training, validation and testing for a total of

$60$ epochs.

Use class and objects