How d2l-ai/d2l-zh works
D2L is an open, practice-oriented deep-learning textbook accompanied by runnable examples and framework-specific helper libraries. The main reader workflow is to study mathematical and computational foundations, learn model and training methods, apply them to vision and language tasks, and explore performance and deployment topics; examples use the d2l adapters with frameworks and datasets. The graph groups the book’s major documented subject areas and its internal code layer. README and the sampled adapter sources support the overall workflow, but do not establish detailed calls among unsampled chapter subsystems.
Main entry points: __init__.py Framework Helpers · torch.py PyTorch Adapter · tensorflow.py TensorFlow Adapter · mxnet.py MXNet Adapter
Components 24
Foundations
- Introduction
chapter_introduction/index.md - Math And Data
chapter_preliminaries/index.md
Models And Methods
- Linear Networks
chapter_linear-networks/index.md - Multilayer Networks
chapter_multilayer-perceptrons/index.md - Optimization
chapter_optimization/index.md - Model Computation
chapter_deep-learning-computation/index.md - Convolutional Models
chapter_convolutional-neural-networks/index.md - Modern Vision Models
chapter_convolutional-modern/index.md - Recurrent Models
chapter_recurrent-neural-networks/index.md - Attention And Transformers
chapter_attention-mechanisms/index.md
Applications
- Computer Vision
chapter_computer-vision/index.md - Language Pretraining
chapter_natural-language-processing-pretraining/index.md - Language Applications
chapter_natural-language-processing-applications/index.md
Systems And Tools
- Performance And Scaling
chapter_computational-performance/index.md - Tools And Deployment
chapter_appendix-tools-for-deep-learning/index.md
Example Runtime
- Framework Helpers
d2l/__init__.py - PyTorch Adapter
d2l/torch.py - TensorFlow Adapter
d2l/tensorflow.py - MXNet Adapter
d2l/mxnet.py - Paddle Adapter
d2l/paddle.py
Other components
- Reader / Learner
- ML Frameworks
- Dataset Hosting
- Reader Discussion
Connections 36
- Reader / Learner → Introduction: starts with
- Reader / Learner → Math And Data: studies
- Reader / Learner → Linear Networks: studies
- Reader / Learner → Multilayer Networks: studies
- Reader / Learner → Optimization: studies
- Reader / Learner → Model Computation: studies
- Reader / Learner → Convolutional Models: studies
- Reader / Learner → Modern Vision Models: studies
- Reader / Learner → Recurrent Models: studies
- Reader / Learner → Attention And Transformers: studies
- Reader / Learner → Computer Vision: applies methods
- Reader / Learner → Language Pretraining: studies
- Reader / Learner → Language Applications: applies methods
- Reader / Learner → Performance And Scaling: explores scaling
- Reader / Learner → Tools And Deployment: consults
- Linear Networks → Framework Helpers: examples use
- Multilayer Networks → Framework Helpers: examples use
- Convolutional Models → Framework Helpers: examples use
- Recurrent Models → Framework Helpers: examples use
- Attention And Transformers → Framework Helpers: examples use
- Computer Vision → Framework Helpers: examples use
- Language Pretraining → Framework Helpers: examples use
- Language Applications → Framework Helpers: examples use
- Framework Helpers → PyTorch Adapter: selects backend
- Framework Helpers → TensorFlow Adapter: selects backend
- Framework Helpers → MXNet Adapter: selects backend
- Framework Helpers → Paddle Adapter: selects backend
- PyTorch Adapter → ML Frameworks: uses
- TensorFlow Adapter → ML Frameworks: uses
- MXNet Adapter → ML Frameworks: uses
- Paddle Adapter → ML Frameworks: uses
- PyTorch Adapter → Dataset Hosting: downloads datasets
- TensorFlow Adapter → Dataset Hosting: downloads datasets
- MXNet Adapter → Dataset Hosting: downloads datasets
- Paddle Adapter → Dataset Hosting: downloads datasets
- Reader / Learner → Reader Discussion: asks questions