Torchvision

Q: How deeply does Inside Deep Learning: Math, Algorithms, Models cover torchvision?

Explains dataset loading, train-test selection, PIL conversion, tensor ranges, and image shapes, but not broader library internals.

As explained in Inside Deep Learning: Math, Algorithms, Models

A PyTorch companion library for computer-vision data loading and transforms used here to access MNIST and convert images to tensors.

torchvision is a PyTorch companion library for loading image datasets and converting image objects into tensors. It provides a convenient MNIST loader for quick computer-vision experiments. section 3.1.1

A typical MNIST workflow uses torchvision to:

Download and select the predefined training or testing split. section 3.1.1
Apply transforms.ToTensor() so PIL images become tensors with values from 0.0 to 1.0. section 3.1.1
Expose grayscale MNIST examples with shape (1, 28, 28): one channel, 28-pixel width, and 28-pixel height. section 3.1.1

Load MNIST as tensors

Use torchvision.datasets.MNIST("./data", train=True, download=True, transform=transforms.ToTensor()) for training data, and change train to False for testing data.

How Inside Deep Learning: Math, Algorithms, Models covers it

Cover of Inside Deep Learning: Math, Algorithms, Models

liveBook manning.com

Read Inside Deep Learning: Math, Algorithms, Models on liveBook Get the book at manning.com

Related concepts

CIFAR-10uses · CIFAR-10 is a labeled image-classification dataset containing 60,000 32-by-32 color images from ten classes, divided into training and test sets.
Hugging Face Datasetsuses · Hugging Face Datasets is an open-source Python library for loading, processing, managing, and sharing machine-learning datasets.
ResNet50uses · ResNet50 is a 50-layer residual convolutional neural network architecture for visual recognition and image processing.
PyTorchkind of · PyTorch is an open-source machine-learning framework for Python that provides tensor computation, automatic differentiation, and tools for building and training neural networks.

This explainer was generated by Manning's knowledge graph from the text of Inside Deep Learning: Math, Algorithms, Models. The section links point to the parts of the book it draws on.