最新章節

• Leave a review - let other readers know what you think
• Other Books You May Enjoy
• Summary
• How to keep yourself updated
• Open Neural Network Exchange
• fast.ai – making neural nets uncool again

• Leave a review - let other readers know what you think 更新時間：2021-06-24 19:17:02
• Other Books You May Enjoy
• Summary
• How to keep yourself updated
• Open Neural Network Exchange
• fast.ai – making neural nets uncool again
• Alien NLP
• OpenNMT in PyTorch
• Image segmentation
• Object detection
• Interesting ideas to explore
• Overview
• What next?
• What Next?
• Summary
• Decoder
• Encoder
• Encoder-decoder architecture
• Training and validating the model
• Creating an ensembling model
• Creating a custom dataset along with data loaders
• Extracting the image features
• Creating models
• Model ensembling
• Creating a fully connected model and train
• Creating a dataset and loaders
• Extracting DenseNet features
• Creating a DenseNet model
• DenseLayer
• DenseBlock
• Densely connected convolutional networks – DenseNet
• Training and validating the model
• Creating a fully connected model
• Creating a new dataset for the convoluted features
• Extracting convolutional features using register_forward_hook
• Creating an Inception model
• Inception
• Training and validating the model
• Creating a simple linear model
• Creating a custom PyTorch dataset class for the pre-convoluted features and loader
• Extracting convolutional features
• Creating a ResNet model
• Creating loaders for training and validation
• Creating PyTorch datasets
• ResNet
• Modern network architectures
• Modern Network Architectures
• Summary
• Training the model
• Defining the train and evaluate functions
• Defining a model based on LSTM
• Backpropagation through time
• Batches
• Generating the batches
• Preparing the data
• Language modeling
• Inspecting the generated images
• Training the complete network
• Training the generator network
• Training the discriminator with fake images
• Training the discriminator with real images
• Training the discriminator
• Defining loss and optimizer
• Defining the discriminator network
• Generator
• Batch normalization
• Transposed convolutions
• Defining the generator network
• Deep convolutional GAN
• Generative adversarial networks
• Training
• Creating the optimizer
• Creating loss function for each layers
• Extracting the losses
• Style loss
• Content loss
• Creating the VGG model
• Loading the data
• Neural style transfer
• Generative Networks
• Summary
• Training the model
• Creating the network
• Understanding one-dimensional convolution for sequence data
• Convolutional network on sequence data
• Training the model
• Creating the network
• Creating batches
• Preparing the data
• LSTM networks
• Long-term dependency
• LSTM
• Understanding how RNN works with an example
• Recursive neural networks
• Freeze the embedding layer weights
• Loading the embeddings in the model
• Downloading the embeddings
• Using pretrained word embeddings
• Training the model
• Creating a network model with embedding
• Generate batches of vectors
• Building vocabulary
• torchtext.datasets
• torchtext.data
• Downloading IMDB data and performing text tokenization
• Training word embedding by building a sentiment classifier
• Word embedding
• One-hot encoding
• Vectorization
• N-gram representation
• Converting text into words
• Converting text into characters
• Tokenization
• Working with text data
• Deep Learning with Sequence Data and Text
• Summary
• Visualizing weights of the CNN layer
• Visualizing outputs from intermediate layers
• Understanding what a CNN model learns
• Calculating pre-convoluted features
• Training the VGG16 model
• Fine-tuning VGG16
• Freezing the layers
• Creating and exploring a VGG16 model
• Classifying dogs and cats using transfer learning
• Classifying dogs and cats – CNN from scratch
• Training the model
• Linear layer
• View
• Nonlinear activation – ReLU
• Pooling
• Conv2d
• Building a CNN model from scratch
• MNIST – getting data
• Introduction to neural networks
• Deep Learning for Computer Vision
• Summary
• Learning rate picking strategies
• Applying regularization
• Large model enough to overfit
• Baseline model
• Prepare your data
• Evaluation protocol
• Measure of success
• Problem definition and dataset creation
• Workflow of a machine learning project
• Underfitting
• Dropout
• Applying weight regularization
• Reducing the size of the network
• Getting more data
• Overfitting and underfitting
• Feature engineering
• Handling missing values
• Value normalization
• Vectorization
• Data preprocessing and feature engineering
• Data redundancy
• Time sensitivity
• Data representativeness
• K-fold validation with shuffling
• K-fold validation
• Simple holdout validation
• Training validation and test split
• Evaluating machine learning models
• Machine learning glossary
• Reinforcement learning
• Unsupervised learning
• Supervised learning
• Three kinds of machine learning problems
• Fundamentals of Machine Learning
• Summary
• Training the model
• Building the network architecture
• Loading PyTorch tensors as batches
• Loading data into PyTorch tensors
• Image classification using deep learning
• Optimizing network architecture
• Loss functions
• Model architecture for different machine learning problems
• The PyTorch way of building deep learning algorithms
• PyTorch non-linear activations
• Leaky ReLU
• ReLU
• Tanh
• Sigmoid
• Non-linear activations
• Layers – fundamental blocks of neural networks
• Deep dive into the building blocks of neural networks
• Diving Deep into Neural Networks
• Summary
• DataLoader class
• Dataset class
• Loading data
• Optimize the neural network
• Loss function
• Network implementation
• Neural network model
• Creating learnable parameters
• Creating data for our neural network
• Variables
• Tensors on GPU
• 5-D tensors
• 4-D tensors
• Slicing tensors
• 3-D tensors
• Matrix (2-D tensors)
• Vectors (1-D tensors)
• Scalar (0-D tensors)
• Data preparation
• Our first neural network
• Installing PyTorch
• Building Blocks of Neural Networks
• Summary
• PyTorch
• Deep learning frameworks
• Data and algorithms
• Hardware availability
• Why now?
• The history of deep learning
• Hype associated with deep learning
• Applications of deep learning
• Deep learning
• Examples of machine learning in real life
• Machine learning
• The history of AI
• Artificial intelligence
• Getting Started with Deep Learning Using PyTorch
• Reviews
• Get in touch
• Conventions used
• Download the color images
• Download the example code files
• To get the most out of this book
• What this book covers
• Who this book is for
• Preface
• Packt is searching for authors like you
• About the reviewer
• About the author
• Contributors
• Foreword
• PacktPub.com
• Why subscribe?
• Packt Upsell
• Dedication
• Title Page
• coverpage

• coverpage
• Title Page
• Dedication
• Packt Upsell
• Why subscribe?
• PacktPub.com
• Foreword
• Contributors
• About the author
• About the reviewer
• Packt is searching for authors like you
• Preface
• Who this book is for
• What this book covers
• To get the most out of this book
• Download the example code files
• Download the color images
• Conventions used
• Get in touch
• Reviews
• Getting Started with Deep Learning Using PyTorch
• Artificial intelligence
• The history of AI
• Machine learning
• Examples of machine learning in real life
• Deep learning
• Applications of deep learning
• Hype associated with deep learning
• The history of deep learning
• Why now?
• Hardware availability
• Data and algorithms
• Deep learning frameworks
• PyTorch
• Summary
• Building Blocks of Neural Networks
• Installing PyTorch
• Our first neural network
• Data preparation
• Scalar (0-D tensors)
• Vectors (1-D tensors)
• Matrix (2-D tensors)
• 3-D tensors
• Slicing tensors
• 4-D tensors
• 5-D tensors
• Tensors on GPU
• Variables
• Creating data for our neural network
• Creating learnable parameters
• Neural network model
• Network implementation
• Loss function
• Optimize the neural network
• Loading data
• Dataset class
• DataLoader class
• Summary
• Diving Deep into Neural Networks
• Deep dive into the building blocks of neural networks
• Layers – fundamental blocks of neural networks
• Non-linear activations
• Sigmoid
• Tanh
• ReLU
• Leaky ReLU
• PyTorch non-linear activations
• The PyTorch way of building deep learning algorithms
• Model architecture for different machine learning problems
• Loss functions
• Optimizing network architecture
• Image classification using deep learning
• Loading data into PyTorch tensors
• Loading PyTorch tensors as batches
• Building the network architecture
• Training the model
• Summary
• Fundamentals of Machine Learning
• Three kinds of machine learning problems
• Supervised learning
• Unsupervised learning
• Reinforcement learning
• Machine learning glossary
• Evaluating machine learning models
• Training validation and test split
• Simple holdout validation
• K-fold validation
• K-fold validation with shuffling
• Data representativeness
• Time sensitivity
• Data redundancy
• Data preprocessing and feature engineering
• Vectorization
• Value normalization
• Handling missing values
• Feature engineering
• Overfitting and underfitting
• Getting more data
• Reducing the size of the network
• Applying weight regularization
• Dropout
• Underfitting
• Workflow of a machine learning project
• Problem definition and dataset creation
• Measure of success
• Evaluation protocol
• Prepare your data
• Baseline model
• Large model enough to overfit
• Applying regularization
• Learning rate picking strategies
• Summary
• Deep Learning for Computer Vision
• Introduction to neural networks
• MNIST – getting data
• Building a CNN model from scratch
• Conv2d
• Pooling
• Nonlinear activation – ReLU
• View
• Linear layer
• Training the model
• Classifying dogs and cats – CNN from scratch
• Classifying dogs and cats using transfer learning
• Creating and exploring a VGG16 model
• Freezing the layers
• Fine-tuning VGG16
• Training the VGG16 model
• Calculating pre-convoluted features
• Understanding what a CNN model learns
• Visualizing outputs from intermediate layers
• Visualizing weights of the CNN layer
• Summary
• Deep Learning with Sequence Data and Text
• Working with text data
• Tokenization
• Converting text into characters
• Converting text into words
• N-gram representation
• Vectorization
• One-hot encoding
• Word embedding
• Training word embedding by building a sentiment classifier
• Downloading IMDB data and performing text tokenization
• torchtext.data
• torchtext.datasets
• Building vocabulary
• Generate batches of vectors
• Creating a network model with embedding
• Training the model
• Using pretrained word embeddings
• Downloading the embeddings
• Loading the embeddings in the model
• Freeze the embedding layer weights
• Recursive neural networks
• Understanding how RNN works with an example
• LSTM
• Long-term dependency
• LSTM networks
• Preparing the data
• Creating batches
• Creating the network
• Training the model
• Convolutional network on sequence data
• Understanding one-dimensional convolution for sequence data
• Creating the network
• Training the model
• Summary
• Generative Networks
• Neural style transfer
• Loading the data
• Creating the VGG model
• Content loss
• Style loss
• Extracting the losses
• Creating loss function for each layers
• Creating the optimizer
• Training
• Generative adversarial networks
• Deep convolutional GAN
• Defining the generator network
• Transposed convolutions
• Batch normalization
• Generator
• Defining the discriminator network
• Defining loss and optimizer
• Training the discriminator
• Training the discriminator with real images
• Training the discriminator with fake images
• Training the generator network
• Training the complete network
• Inspecting the generated images
• Language modeling
• Preparing the data
• Generating the batches
• Batches
• Backpropagation through time
• Defining a model based on LSTM
• Defining the train and evaluate functions
• Training the model
• Summary
• Modern Network Architectures
• Modern network architectures
• ResNet
• Creating PyTorch datasets
• Creating loaders for training and validation
• Creating a ResNet model
• Extracting convolutional features
• Creating a custom PyTorch dataset class for the pre-convoluted features and loader
• Creating a simple linear model
• Training and validating the model
• Inception
• Creating an Inception model
• Extracting convolutional features using register_forward_hook
• Creating a new dataset for the convoluted features
• Creating a fully connected model
• Training and validating the model
• Densely connected convolutional networks – DenseNet
• DenseBlock
• DenseLayer
• Creating a DenseNet model
• Extracting DenseNet features
• Creating a dataset and loaders
• Creating a fully connected model and train
• Model ensembling
• Creating models
• Extracting the image features
• Creating a custom dataset along with data loaders
• Creating an ensembling model
• Training and validating the model
• Encoder-decoder architecture
• Encoder
• Decoder
• Summary
• What Next?
• What next?
• Overview
• Interesting ideas to explore
• Object detection
• Image segmentation
• OpenNMT in PyTorch
• Alien NLP
• fast.ai – making neural nets uncool again
• Open Neural Network Exchange
• How to keep yourself updated
• Summary
• Other Books You May Enjoy
• Leave a review - let other readers know what you think 更新時間：2021-06-24 19:17:02