Pytorch
Basics
PyTorch is an open-source machine-learning and deep-learning framework developed by Meta.
Tensor
Tensors are the fundamental building block of machine learning in PyTorch — learn what they are, how to manipulate them, and how to use them on a GPU.
Workflow
A full PyTorch model cycle — data, model, training, evaluation and saving — illustrated step by step on a regression problem.
Custom datasets
Load your own data into PyTorch with Dataset, DataLoader, ImageFolder, samplers and a transforms pipeline.
Classification
Train neural networks to assign discrete labels — binary and multi-class classification with PyTorch.
Vision
Train convolutional neural networks on image data with PyTorch and torchvision — from FashionMNIST warm-up to an MNIST capstone.
Transfer learning
Reuse pretrained torchvision models on your own dataset to reach strong accuracy with very little data and very little training time.