Chapter 13 sections from Deep Learning with PyTorch.
6 items
Image classification assigns one label, or a small set of labels, to an image.
Transfer learning reuses a model trained on one task as the starting point for another task.
Fine-tuning adapts a pretrained model to a target dataset by continuing training from learned weights instead of starting from random initialization.
Data augmentation creates modified versions of training examples without changing their labels.
Large-scale training means training models on datasets, model sizes, or hardware configurations that exceed a simple single-GPU workflow.
A classifier returns scores. Users often interpret those scores as confidence. This interpretation is safe only when the scores are calibrated. A calibrated model assigns probabilities that match empirical correctness.