What is torch.nn really?

Resource history | v1 (current) | created by janarez on Mar 12, 2021

Details

Title: What is torch.nn really?
Type: Web
Created: no value
Description: PyTorch provides the elegantly designed modules and classes torch.nn , torch.optim , Dataset , and DataLoader to help you create and train neural networks. In order to fully utilize their power and customize them for your problem, you need to really understand exactly what they’re doing. To develop this understanding, we will first train basic neural net on the MNIST data set without using any features from these models; we will initially only use the most basic PyTorch tensor functionality. Then, we will incrementally add one feature from torch.nn, torch.optim, Dataset, or DataLoader at a time, showing exactly what each piece does, and how it works to make the code either more concise, or more flexible.
Link: https://pytorch.org/tutorials/beginner/nn_tutorial.html
Identifier: no value

This resource has no history of related authors.

This resource has no history of related resources.