# dsgiitr/d2l-pytorch

This project reproduces the book Dive Into Deep Learning (https://d2l.ai/), adapting the code from MXNet into PyTorch.

Repository: https://github.com/dsgiitr/d2l-pytorch
Canonical: https://ross.abutalabs.com/products/d2l-pytorch
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: deep-learning, d2l, data-science, pytorch-implmention, book, nlp, computer-vision, pytorch, mxnet, dive-into-deep-learning
Last push: 2024-07-25T11:01:42+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2671, "days_push": 769, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4359, forks 1232 (observed 2026-08-28T04:08:46.543247+00:00)

## What it is
A Jupyter Notebook adaptation of the 'Dive Into Deep Learning' book, converting its MXNet code examples into PyTorch. It covers deep learning fundamentals from linear regression through NLP and computer vision topics.

## Use cases
- learn deep learning with PyTorch
- study the Dive Into Deep Learning book with PyTorch code
- find PyTorch implementations of classic deep learning models
- learn linear regression and softmax regression from scratch
- study CNNs, RNNs, and attention mechanisms with runnable notebooks
- get a hands-on introduction to NLP and computer vision in PyTorch

## When to choose
- you want to learn deep learning theory alongside runnable PyTorch code
- you prefer PyTorch over MXNet for the D2L book
- you want free, notebook-based deep learning tutorials

## When to avoid
- you need the complete, up-to-date PyTorch port of D2L (use the official d2l-ai/d2l-en repo)
- you need a maintained library or production tooling
- you want MXNet-based examples

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: deep-learning, machine-learning, nlp, computer-vision
- domain: deep-learning, machine-learning, tutorials, education
- platform: python
- tags: pytorch, jupyter-notebooks, d2l, book-adaptation, educational

## Member repositories
- dsgiitr/d2l-pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:46.543247+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:21:27.923171+00:00, confidence not recorded.
  - readme: https://github.com/dsgiitr/d2l-pytorch (fetched 2026-08-28T04:08:46.543247+00:00, sha d91be9d2693b)
- Data as of 2026-08-30T08:39:29.467469+00:00.