Seven new tutorials:

  • PyTorch Chinese tutorial 1.7
    • Learning PyTorch
      • PyTorch Deep Learning: 60 minutes of assault
        • tensor
        • torch.autogradA brief introduction to
        • The neural network
        • Training classifier
      • Learn PyTorch by example
        • Warm up: NumPy
        • PyTorch: tensor
        • PyTorch: Tensor and Autograd
        • PyTorch: Define a new Autograd function
        • PyTorch:nn
        • PyTorch:optim
        • PyTorch: CustomnnThe module
        • PyTorch: Control flow + weight sharing
      • torch.nnWhat is it?
      • Visualize models, data, and training using TensorBoard
    • Pictures/Videos
      • torchvisionObject detection fine tuning tutorial
      • Transfer learning tutorial for computer vision
      • Counter example generation
      • DCGAN tutorial
    • audio
      • Audio I/O andtorchaudioThe pretreatment of the
      • usetorchaudioVoice command recognition
    • The text
      • usenn.TransformerandtorchtextSequence to sequence modeling
      • NLP from scratch: Classification names using character-level RNN
      • NLP from scratch: Generates names using character-level RNN
      • NLP from scratch: Translation using sequence to sequence networks and attention
      • usetorchtextText classification of
      • torchtextLanguage translation
    • Reinforcement learning
      • Reinforcement learning (DQN) tutorial
      • Train the RL intelligence to play Mario
    • Deploy the PyTorch model in production
      • PyTorch is deployed in Python using Flask’s REST API
      • TorchScript profile
      • Load the TorchScript model in C++
      • Export the model from PyTorch to ONNX and run it using the ONNX runtime (optional)
    • The front-end API
      • Introduction to naming tensors in PyTorch (prototype)
      • PyTorch channels in final memory format (beta)
      • Use PyTorch C++ front end
      • Custom C++ and CUDA extensions
      • Extend TorchScript with custom C++ operators
      • Extend TorchScript with custom C++ classes
      • Dynamic parallelism in TorchScript
      • Autograd in the C++ front end
      • Register scheduling operators in C++
    • Model optimization
      • Analyze your PyTorch module
      • Use Ray Tune’s hyperparameter tuning
      • Model Clipping Tutorial
      • Dynamic Quantization on LSTM Word Language Model (Beta)
      • Dynamic Quantization on BERT (Beta)
      • Static quantization using Eager mode in PyTorch (Beta)
      • Quantitative Transfer Learning Course for Computer Vision (Beta)
    • Parallel and distributed training
      • PyTorch Distributed overview
      • Single machine model parallel best practices
      • Introduction to distributed data parallelism
      • Write distributed applications with PyTorch
      • Introduction to distributed RPC framework
      • Parameter server is implemented using distributed RPC framework
      • Distributed pipe parallelization using RPC
      • Batch RPC processing using asynchronous execution
      • Will be distributedDataParallelCombined with distributed RPC framework
  • PyTorch WORKSHOP on ARTIFICIAL Intelligence
    • Zero, preface,
    • Introduction to Deep learning and PyTorch
    • Second, the building blocks of neural networks
    • 3. Classification problems using DNN
    • Convolutional neural network
    • Fifth, style transfer
    • 6. Use RNN to analyze data sequence
    • Seven, the appendix
  • A practical guide to learning Python once
    • Zero, preface,
    • Part ONE: an introduction to learning
      • A brief introduction to learning
    • Part TWO: Deep learning architecture
      • 2. Indicator – based approach
      • Model-based approach
      • 4. Optimization based methods
    • Part THREE: Other methods and conclusions
      • Fifth, the method based on generation modeling
      • Summary and other methods
  • A practical guide to Python natural language processing
    • Zero, preface,
    • Part I: Essentials of PyTorch 1.x for NLP
      • I. Fundamentals of machine learning and deep learning
      • Introduction to PyTorch 1.x for NLP
    • Part II: Fundamentals of natural language processing
      • NLP and text embedding
      • 4. Text preprocessing, word stem extraction and word form restoration
    • Part 3: Practical NLP applications using PyTorch 1.x
      • 5. Recurrent neural networks and emotion analysis
      • Convolutional neural networks for text classification
      • Text translation using sequential to sequential neural networks
      • 8. Use attention-based neural networks to build chatbots
      • Nine, the road ahead
  • PyTorch AI basics
    • Zero, preface,
    • PyTorch uses tensors
    • Second, cooperate with neural network
    • Convolutional neural networks for computer vision
    • Circulating neural network for NLP
    • 5. Transfer learning and TensorBoard
    • Explore generative adversarial networks
    • Deep reinforcement learning
    • Build AI models in PyTorch
  • PyTorch Practical guide to deep learning
    • Zero, preface,
    • Deep Learning drill and Introduction to PyTorch
    • Two, simple neural network
    • 3. Deep learning workflow
    • Computer vision
    • 5. Sequence data processing
    • Generate a network
    • 7. Intensive learning
    • PyTorch in production
  • TensorFlow reinforcement learning
    • Zero, preface,
    • Deep learning — architecture and frameworks
    • 2. Use OpenAI Gym to strengthen learning intelligence
    • 3. Markov decision-making process
    • Strategy gradient
    • Q learning and deep Q network
    • 6. Asynchronous methods
    • Everything is robot – a real strategy game
    • AlphaGo — reinforcement learning at its best
    • Reinforcement learning in autonomous driving
    • Financial portfolio management
    • Reinforcement learning in robotics
    • Deep reinforcement learning in advertising technology
    • Reinforcement learning in image processing
    • Deep reinforcement learning in NLP
    • 15. Other topics of reinforcement learning

download

Docker

Docker pull apachecn0/apachecn-dl-zh docker run-tid -p <port>:80 apachecn0/apachecn-dl-zh # visit http://localhost:{port}Copy the code

PYPI

PIP install apachecn-dl-zh apachecn-dl-zh <port> # visit http://localhost:{port}Copy the code

NPM

NPM install -g apachecn-dl-zh apachecn-dl-zh <port> # visit http://localhost:{port}Copy the code

Contribution to guide

This project needs to be proofread, everyone is welcome to submit the Pull Request.

Please be brave to translate and improve your translation. While we strive for excellence, we don’t expect you to be perfect, so don’t worry about making translation mistakes – in most cases, our servers already record all translations, so you don’t have to worry about irreparably damaging your mistakes. (Adapted from Wikipedia)