เขียนคลาสชุดข้อมูลแบบกำหนดเอง

Before a model can learn, PyTorch needs a clean way to reach your samples one at a time. That front door is a Dataset class. 🚪

You build a custom dataset by subclassing torch.utils.data.Dataset. PyTorch then knows exactly how to ask your object for data.

The __init__ method runs once when you create the dataset. Use it to load file paths, arrays, or labels into the object's fields.

A working dataset only needs two methods: __len__ to report its size and __getitem__ to fetch one sample. That is the whole contract.

The __len__ method returns how many samples you have. PyTorch reads this to know when an epoch ends and how far an index can go.

Given an index, __getitem__ returns a single sample, usually a feature and its label. This is where one row of data is handed over.

__getitem__ should hand back tensors so the model can use them directly. Convert NumPy arrays or Python lists right here if needed.

For huge datasets, do not load everything in __init__. Instead read each file inside __getitem__ so only one sample sits in memory at a time.

__getitem__ is the natural place to apply a transform, like resizing an image. Store the transform in __init__, then call it before returning.

Once built, your dataset behaves like a list. Calling len(ds) or ds[0] just triggers the two methods you defined. Test it before training.

This tidy interface is why a custom Dataset drops straight into a DataLoader. You write two methods and the rest of PyTorch just works.

Which method does PyTorch call to fetch a single sample by index?

A custom dataset subclasses Dataset and defines two methods: __len__ for its size and __getitem__ to return one sample. Two methods, full power. 🎉