I found this useful for dataset and dataloader. Though, the article contains a good, overall summary of PyTorch.
https://towardsdatascience.com/understanding-pytorch-with-an-example-a-step-by-step-tutorial-81fc5f8c4e8e#2e24
A detailed post about preprocessing data in PyTorch.
https://towardsdatascience.com/building-efficient-custom-datasets-in-pytorch-2563b946fd9f
Explains image preprocessing techniques (i.e. brightness, color) as they fit in with PyTorch.
https://www.cs.virginia.edu/~vicente/recognition/notebooks/image_processing_lab.html
Explaining what "sampling" meant
https://kevinmusgrave.github.io/pytorch-metric-learning/samplers/