Deep Learning with PyTorch

Deep Learning with PyTorch

January 1, 2020
  • Outline
    • Part 1 Core PyTorch
      • 1 Introducing deep learning and the PyTorch library
        • 1.1 What is PyTorch? 2
        • 1.2 What is this book? 2
        • 1.3 Why PyTorch? 3
        • 1.4 PyTorch has the batteries included 10
      • 2 It starts with a tensor
        • 2.1 Tensor fundamentals 18
        • 2.2 Tensors and storages 22
        • 2.3 Size, storage offset, and strides 24
        • 2.4 Numeric types 30
        • 2.5 Indexing tensors 31
        • 2.6 NumPy interoperability 31
        • 2.7 Serializing tensors 32
        • 2.8 Moving tensors to the GPU 34
        • 2.9 The tensor API 35
      • 3 Real-world data representation with tensors
        • 3.1 Tabular data
        • 3.2 Time series
        • 3.3 Text
        • 3.4 Images
        • 3.5 Volumetric data
      • 4 The mechanics of learning 67
        • 4.1 Learning is parameter estimation 70
        • 4.2 PyTorch’s autograd: Backpropagate all things 83
      • 5 Using a neural network to fit your data 101
        • 5.1 Artificial neurons 102
        • 5.2 The PyTorch nn module 110
        • 5.3 Subclassing nn.Module 120
    • Part 2 Learning from images in the real world: Early detection of lung cancer
    • Part 3 Deployment
  • Links