Advanced applied deep learning convolutional neural networks and object detection /
Develop and optimize deep learning models with advanced architectures. This book teaches you the intricate details and subtleties of the algorithms that are at the core of convolutional neural networks. In Advanced Applied Deep Learning, you will study advanced topics on CNN and object detection usi...
| Main Author: | Michelucci, Umberto, |
|---|---|
| Other Authors: | SpringerLink (Online Service) |
| Format: | eBook |
| Language: | English |
| Published: |
New York :
Apress,
[2019]
|
| Physical Description: |
1 online resource : illustrations (some color) |
| Subjects: |
Table of Contents:
- Intro; Table of Contents; About the Author; About the Technical Reviewer; Acknowledgments; Introduction; Chapter 1: Introduction and Development Environment Setup; GitHub Repository and Companion Website; Mathematical Level Required; Python Development Environment; Google Colab; Benefits and Drawbacks to Google Colab; Anaconda; Installing TensorFlow the Anaconda Way; Local Jupyter Notebooks; Benefits and Drawbacks to Anaconda; Docker Image; Benefits and Drawbacks to a Docker Image; Which Option Should You Choose?; Chapter 2: TensorFlow: Advanced Topics; Tensorflow Eager Execution.
- Enabling Eager ExecutionPolynomial Fitting with Eager Execution; MNIST Classification with Eager Execution; TensorFlow and Numpy Compatibility; Hardware Acceleration; Checking the Availability of the GPU; Device Names; Explicit Device Placement; GPU Acceleration Demonstration: Matrix Multiplication; Effect of GPU Acceleration on the MNIST Example; Training Only Specific Layers; Training Only Specific Layers: An Example; Removing Layers; Keras Callback Functions; Custom Callback Class; Example of a Custom Callback Class; Save and Load Models; Save Your Weights Manually; Saving the Entire Model.
- Dataset AbstractionIterating Over a Dataset; Simple Batching; Simple Batching with the MNIST Dataset; Using tf.data. Dataset in Eager Execution Mode; Conclusions; Chapter 3: Fundamentals of Convolutional Neural Networks; Kernels and Filters; Convolution; Examples of Convolution; Pooling; Padding; Building Blocks of a CNN; Convolutional Layers; Pooling Layers; Stacking Layers Together; Number of Weights in a CNN; Convolutional Layer; Pooling Layer; Dense Layer; Example of a CNN: MNIST Dataset; Visualization of CNN Learning; Brief Digression: keras.backend.function(); Effect of Kernels.
- Effect of Max-PoolingChapter 4: Advanced CNNs and Transfer Learning; Convolution with Multiple Channels; History and Basics of Inception Networks; Inception Module: Naïve Version; Number of Parameters in the Naïve Inception Module; Inception Module with Dimension Reduction; Multiple Cost Functions: GoogLeNet; Example of Inception Modules in Keras; Digression: Custom Losses in Keras; How To Use Pre-Trained Networks; Transfer Learning: An Introduction; A Dog and Cat Problem; Classical Approach to Transfer Learning; Experimentation with Transfer Learning.
- Chapter 5: Cost Functions and Style TransferComponents of a Neural Network Model; Training Seen as an Optimization Problem; A Concrete Example: Linear Regression; The Cost Function; Mathematical Notation; Typical Cost Functions; Mean Square Error; Intuitive Explanation; MSE as the Second Moment of a Moment-Generating Function; Cross-Entropy; Self-Information or Suprisal of an Event; Suprisal Associated with an Event X; Cross-Entropy; Cross-Entropy for Binary Classification; Cost Functions: A Final Word; Neural Style Transfer; The Mathematics Behind NST; An Example of Style Transfer in Keras.