December 2018
Intermediate to advanced
158 pages
3h 58m
English
Pytorch includes data loaders for several datasets to help you get started. The torch.dataloader is the class used for loading datasets. The following is a list of the included torch datasets and a brief description:
|
MNIST |
Handwritten digits 1–9. A subset of NIST dataset of handwritten characters. Contains a training set of 60,000 test images and a test set of 10,000. |
|
Fashion- MNIST |
A drop-in dataset for MNIST. Contains images of fashion items; for example, T-shirt, trousers, pullover. |
|
EMNIST |
Based on NIST handwritten characters, including letters and numbers and split for 47, 26, and 10 class classification problems. |
|
COCO |
Over 100,000 images classified into everyday objects; for example, person, ... |
Read now
Unlock full access