What is torch.nn really?


Resource | v1 | created by janarez |
Type Web
Created unavailable
Identifier unavailable

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.

Relations

about PyTorch

PyTorch is an open source machine learning library based on the Torch library, used for applications...


Edit details Edit relations Attach new author Attach new topic Attach new resource
10.0 /10
useless alright awesome
from 1 review
Write comment Rate resource Tip: Rating is anonymous unless you also write a comment.
Resource level 1.0 /10
beginner intermediate advanced
Resource clarity 10.0 /10
hardly clear sometimes unclear perfectly clear
Reviewer's background 4.0 /10
none basics intermediate advanced expert
Comments 1
janarez
0 0

10 rating 1 level 10 clarity 4 user's background

Clearly explains what each PyTorch code does by replacing vanilla Python code.
None. This is simply great.
Superb for beginners to see behind the most used and basic high-level calls in PyTorch.