d2l

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

Một cuốn sách về Học Sâu đề cập đến nhiều framework phổ biến, được sử dụng trên 300 trường Đại học từ 55 đất nước bao gồm MIT, Stanford, Harvard, và Cambridge.

The Java implementation of Dive into Deep Learning (D2L.ai)

This repository contains Tensorflow 2 code for Attention Mechanisms chapter of Dive into Deep Learning (D2L) book.

Dive to Deep Learning with Pytorch C++ API

A easy tool to download usc den video using just one right click. Using tampermonkey and node.js

Adds a few Quality of Life tweaks to the online educational platform Brightspace Desire2Learn (D2L).

将《动手学深度学习》 原书中MXNet代码实现改为PaddlePaddle实现.

This repository contains Tensorflow 2 code for Generative Adversarial Networks chapter of Dive into Deep Learning (D2L) book.

[WIP] Dive into Deep Learning (Vietnamese Version) https://github.com/d2l-ai/d2l-en

Slides for Dive into Deep Learning book

Learn from *Dive into Deep Learning*, take notes, and do some modification.

This repo provides Pytorch implementation for codes in the book "Dive Into Deep Learning" (http://d2l.ai/) and course Berkeley STAT 157 (https://courses.d2l.ai), which gives a brief tutorial on deep learning methods.

An angular application to easily view and save, data-sets retrieved using Brightspace APIs. Using a Go backend

yasnippet snippets for D2L/Brightspace CSV Question format

IAM-less AWS API access for humans.

Formats and pivots data from Brightspace by D2L intelligent agents and survey reports

Brightspace/Desire2Learn's Python "D2LValence_Util" package.

本项目用OneFlow实现《动手学深度学习 第二版》(Dive into Deep Learning)中的代码

Using the OAuth 2.0 flow to get data from Brightspace APIs.

Practise colabs of self taught deep learning from #d2l

Dive Into Deep Learning (d2l.ai), Using Jax & DeepMind's dm-haiku

learn d2l with clojure

Sync user accounts to d2l lms

Extension to improve the Brightspace/D2L user experience.

This is a series of R Programs used to randomly generate questions and answers within WMU's D2L E-learning system. Several nice features are included or in production, such as user-friendly function wrappers and clear comments to outline the code. The final results are thousands of multiple-choice questions as D2L-compatible CSV and JPG files.