Log In
Or create an account ->
Imperial Library
Home
About
News
Upload
Forum
Help
Login/SignUp
Index
Title Page
Copyright and Credits
Python Deep Learning Projects
Humble Bundle
Dedication
Packt Upsell
Why subscribe?
Packt.com
Contributors
About the authors
About the reviewers
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
Building Deep Learning Environments
Building a common DL environment
Get focused and into the code!
DL environment setup locally
Downloading and installing Anaconda
Installing DL libraries
Setting up a DL environment in the cloud
Cloud platforms for deployment
Prerequisites
Setting up the GCP
Automating the setup process
Summary
Training NN for Prediction Using Regression
Building a regression model for prediction using an MLP deep neural network
Exploring the MNIST dataset
Intuition and preparation
Defining regression
Defining the project structure
Let's code the implementation!
Defining hyperparameters
Model definition
Building the training loop
Overfitting and underfitting
Building inference
Concluding the project
Summary
Word Representation Using word2vec
Learning word vectors
Loading all the dependencies
Preparing the text corpus
Defining our word2vec model
Training the model
Analyzing the model
Plotting the word cluster using the t-SNE algorithm
Visualizing the embedding space by plotting the model on TensorBoard
Building language models using CNN and word2vec
Exploring the CNN model
Understanding data format
Integrating word2vec with CNN
Executing the model
Deploy the model into production
Summary
Building an NLP Pipeline for Building Chatbots
Basics of NLP pipelines
Tokenization
Part-of-Speech tagging
Extracting nouns
Extracting verbs
Dependency parsing
NER
Building conversational bots
What is TF-IDF?
Preparing the dataset
Implementation
Creating the vectorizer
Processing the query
Rank results
Advanced chatbots using NER
Installing Rasa
Preparing dataset
Training the model
Deploying the model
Serving chatbots
Summary
Sequence-to-Sequence Models for Building Chatbots
Introducing RNNs
RNN architectures
Implementing basic RNNs
Importing all of the dependencies
Preparing the dataset
Hyperparameters
Defining a basic RNN cell model
Training the RNN Model
Evaluation of the RNN model
LSTM architecture
Implementing an LSTM model
Defining our LSTM model
Training the LSTM model
Evaluation of the LSTM model
Sequence-to-sequence models
Data preparation
Defining a seq2seq model
Hyperparameters
Training the seq2seq model
Evaluation of the seq2seq model
Summary
Generative Language Model for Content Creation
LSTM for text generation
Data pre-processing
Defining the LSTM model for text generation
Training the model
Inference and results
Generating lyrics using deep (multi-layer) LSTM
Data pre-processing
Defining the model
Training the deep TensorFlow-based LSTM model
Inference
Output
Generating music using a multi-layer LSTM
Pre-processing data
Defining the model and training
Generating music
Summary
Building Speech Recognition with DeepSpeech2
Data preprocessing
Corpus exploration
Feature engineering
Data transformation
DS2 model description and intuition
Training the model
Testing and evaluating the model
Summary
Handwritten Digits Classification Using ConvNets
Code implementation
Importing all of the dependencies
Exploring the data
Defining the hyperparameters
Building and training a simple deep neural network
Fitting a model
Evaluating a model
MLP – Python file
Convolution
Convolution in Keras
Fitting the model
Evaluating the model
Convolution – Python file
Pooling
Fitting the model
Evaluating the model
Convolution with pooling – Python file
Dropout
Fitting the model
Evaluating the model
Convolution with pooling – Python file
Going deeper
Compiling the model
Fitting the model
Evaluating the model
Convolution with pooling and Dropout – Python file
Data augmentation
Using ImageDataGenerator
Fitting ImageDataGenerator
Compiling the model
Fitting the model
Evaluating the model
Augmentation – Python file
Additional topic – convolution autoencoder
Importing the dependencies
Generating low-resolution images
Scaling
Defining the autoencoder
Fitting the autoencoder
Loss plot and test results
Autoencoder – Python file
Conclusion
Summary
Object Detection Using OpenCV and TensorFlow
Object detection intuition
Improvements in object detection models
Object detection using OpenCV
A handcrafted red object detector
Installing dependencies
Exploring image data
Normalizing the image
Preparing a mask
Post-processing of a mask
Applying a mask
Object detection using deep learning
Quick implementation of object detection
Installing all the dependencies
Implementation
Deployment
Object Detection In Real-Time Using YOLOv2
Preparing the dataset
Using the pre-existing COCO dataset
Using the custom dataset
Installing all the dependencies
Configuring the YOLO model
Defining the YOLO v2 model
Training the model
Evaluating the model
Image segmentation
Importing all the dependencies
Exploring the data
Images
Annotations
Preparing the data
Normalizing the image
Encoding
Model data
Defining hyperparameters
Define SegNet
Compiling the model
Fitting the model
Testing the model
Conclusion
Summary
Building Face Recognition Using FaceNet
Setup environment
Getting the code
Building the Docker image
Downloading pre-trained models
Building the pipeline
Preprocessing of images
Face detection
Aligning faces
Feature extraction
Execution on Docker
Training the classifier
Evaluation
Summary
Automated Image Captioning
Data preparation
Initialization
Download and prepare the MS-COCO dataset
Data preparation for a deep CNN encoder
Performing feature extraction
Data prep for a language generation (RNN) decoder
Setting up the data pipeline
Defining the captioning model
Attention
CNN encoder
RNN decoder
Loss function
Training the captioning model
Evaluating the captioning model
Deploying the captioning model
Summary
Pose Estimation on 3D models Using ConvNets
Code implementation
Importing the dependencies
Exploring and pre-processing the data
Preparing the data
Cropping
Resizing
Plotting the joints and limbs
Transforming the images
Defining hyperparameters for training
Building the VGG16 model
Defining the VGG16 model
Training loop
Plot training and validation loss
Predictions
Scripts in modular form
Module 1 – crop_resize_transform.py
Module 2 – plotting.py
Module 3 – test.py
Module 4 – train.py
Conclusion
Summary
Image Translation Using GANs for Style Transfer
Let's code the implementation!
Importing all of the dependencies
Exploring the data
Preparing the data
Type conversion, centering, and scaling
Masking/inserting noise
Reshaping
MNIST classifier
Defining hyperparameters for GAN
Building the GAN model components
Defining the generator
Defining the discriminator
Defining the DCGAN
Training GAN
Plotting the training – part 1
Plotting the training – part 2
Training loop
Predictions
CNN classifier predictions on the noised and generated images
Scripts in modular form
Module 1 – train_mnist.py
Module 2 – training_plots.py
Module 3 – GAN.py
Module 4 – train_gan.py
The conclusion to the project
Summary
Develop an Autonomous Agent with Deep R Learning
Let's get to the code!
Deep Q-learning
Importing all of the dependencies
Exploring the CartPole game
Interacting with the CartPole game
Loading the game
Resetting the game
Playing the game
Q-learning
Defining hyperparameters for Deep Q Learning (DQN)
Building the model components
Defining the agent
Defining the agent action
Defining the memory
Defining the performance plot
Defining replay
Training loop
Testing the DQN model
Deep Q-learning scripts in modular form
Module 1 – hyperparameters_dqn.py
Module 2 – agent_replay_dqn.py
Module 3 – test_dqn.py
Module 4 – train_dqn.py
Deep SARSA learning
SARSA learning
Importing all of the dependencies
Loading the game environment
Defining the agent
Training the agent
Testing the agent
Deep SARSA learning script in modular form
The conclusion to the project
Summary
Summary and Next Steps in Your Deep Learning Career
Python deep learning – building the foundation – two projects
Chapter 1 – Building the Deep Learning Environment
Chapter 2 – Training NN for Prediction Using Regression
Python deep learning – NLP – 5 projects
Chapter 3 – Word Representations Using word2vec
Chapter 4 – Build an NLP Pipeline for Building Chatbots
Chapter 5 – Sequence-to-Sequence Models for Building Chatbots
Chapter 6 – Generative Language Model for Content Creation
Chapter 7 – Building Speech Recognition with DeepSpeech2
Deep learning – computer vision – 6 projects
Chapter 8 – Handwritten Digit Classification Using ConvNets
Chapter 9 – Object Detection Using OpenCV and TensorFlow
Chapter 10 – Building Facial Recognition Using OpenFace
Chapter 11 – Automated Image Captioning
Chapter 12 – Pose Estimation on 3D Models Using ConvNets
Chapter 13 – Image Translation Using GANs for Style Transfer
Python deep learning – autonomous agents – 1 project
Chapter 14 – Develop an Autonomous Agent with Deep Reinforcement Learning
Next steps – AI strategy and platforms
AI strategy
Deep learning platforms – TensorFlow Extended (TFX)
Conclusion and thank you!
Other Books You May Enjoy
Leave a review - let other readers know what you think
← Prev
Back
Next →
← Prev
Back
Next →