TorchVision Datasets: Getting Started

Ben Cook • Posted 2021-10-22 • Code
torchvision datasets mnist 3

The TorchVision datasets subpackage is a convenient utility for accessing well-known public image and video datasets. You can use these tools to start training new computer vision models very quickly. TorchVision Datasets Example To get started, all you have to do is import one of the Dataset classes. Then, instantiate … Read more

PyTorch DataLoader Quick Start

Ben Cook • Posted 2021-10-07 • Last updated 2021-10-18

PyTorch comes with powerful data loading capabilities out of the box. But with great power comes great responsibility and that makes data loading in PyTorch a fairly advanced topic. One of the best ways to learn advanced topics is to start with the happy path. Then add complexity when you … Read more

How to Use the PyTorch Sigmoid Operation

Ben Cook • Posted 2021-05-13 • Last updated 2021-10-14
sigmoid function

The PyTorch sigmoid function is an element-wise operation that squishes any real number into a range between 0 and 1. This is a very common activation function to use as the last layer of binary classifiers (including logistic regression) because it lets you treat model predictions like probabilities that their … Read more

TorchVision Transforms: Image Preprocessing in PyTorch

Ben Cook • Posted 2021-03-19 • Last updated 2021-10-21

TorchVision, a PyTorch computer vision package, has a great API for image pre-processing in its torchvision.transforms module. This post gives some basic usage examples, describes the API and shows you how to create and use custom image transforms.

PyTorch One Hot Encoding

Ben Cook • Posted 2021-02-02 • Last updated 2021-12-13

PyTorch has a one_hot() function for converting class indices to one-hot encoded targets.

The PyTorch Softmax Function

Ben Cook • Posted 2021-01-29 • Last updated 2021-10-14

You can use the top-level torch.softmax() function from PyTorch for your softmax activation needs.

Normalizing Images in PyTorch

Ben Cook • Posted 2021-01-15 • Last updated 2021-10-21
normalized cat image pytorch

You can use the torchvision Normalize() transform to subtract the mean and divide by the standard deviation for image tensors in PyTorch. But it’s important to understand how the transform works and how to reverse it.

Object Tracking in 75 Lines of Code

Ben Cook • Posted 2020-08-01 • Last updated 2022-01-04

Object tracking is pretty easy conceptually. And if you have a good detector, simple methods can be pretty effective.

Cross Entropy Loss in PyTorch

Ben Cook • Posted 2020-07-24 • Last updated 2021-10-14

Cross entropy loss in PyTorch can be a little confusing. Here is a simple explanation of how it works for people who get stuck.