Chapter 14

Chapter 14 sections from Deep Learning with PyTorch.

7 items

Sections

  1. 14.1 Convolution Operations
  2. 14.2 Pooling Layers
  3. 14.3 Feature Maps
  4. 14.4 Padding and Stride
  5. 14.5 CNN Architectures
  6. 14.6 Residual Networks
  7. 14.7 Efficient Convolutions
Writes › Book › Deep Learning with PyTorch › Part IV › Chapter 14 ›

Convolution Operations

Convolution is the central operation in convolutional neural networks.
deep-learning pytorch
Writes › Book › Deep Learning with PyTorch › Part IV › Chapter 14 ›

Pooling Layers

Pooling is a downsampling operation used in convolutional neural networks.
deep-learning pytorch
Writes › Book › Deep Learning with PyTorch › Part IV › Chapter 14 ›

Feature Maps

A feature map is the spatial output produced by a convolutional filter. In a convolutional neural network, each output channel can be read as a map of where a learned feature appears in the input.
deep-learning pytorch
Writes › Book › Deep Learning with PyTorch › Part IV › Chapter 14 ›

Padding and Stride

Padding and stride control the spatial size of convolutional feature maps.
deep-learning pytorch
Writes › Book › Deep Learning with PyTorch › Part IV › Chapter 14 ›

CNN Architectures

A convolutional neural network architecture defines how convolutional layers, activation functions, normalization layers, pooling layers, residual paths, and classifier heads are arranged.
deep-learning pytorch
Writes › Book › Deep Learning with PyTorch › Part IV › Chapter 14 ›

Residual Networks

Residual networks are convolutional networks built from blocks with skip connections.
deep-learning pytorch
Writes › Book › Deep Learning with PyTorch › Part IV › Chapter 14 ›

Efficient Convolutions

Efficient convolutions reduce computation, memory use, or latency while preserving useful spatial modeling.
deep-learning pytorch