Book Image

Python Deep Learning Projects

By : Matthew Lamons, Rahul Kumar, Abhishek Nagaraja
Book Image

Python Deep Learning Projects

By: Matthew Lamons, Rahul Kumar, Abhishek Nagaraja

Overview of this book

Deep learning has been gradually revolutionizing every field of artificial intelligence, making application development easier. Python Deep Learning Projects imparts all the knowledge needed to implement complex deep learning projects in the field of computational linguistics and computer vision. Each of these projects is unique, helping you progressively master the subject. You’ll learn how to implement a text classifier system using a recurrent neural network (RNN) model and optimize it to understand the shortcomings you might experience while implementing a simple deep learning system. Similarly, you’ll discover how to develop various projects, including word vector representation, open domain question answering, and building chatbots using seq-to-seq models and language modeling. In addition to this, you’ll cover advanced concepts, such as regularization, gradient clipping, gradient normalization, and bidirectional RNNs, through a series of engaging projects. By the end of this book, you will have gained knowledge to develop your own deep learning systems in a straightforward way and in an efficient way

Related Content you might be interested in

Current Title:

Small book image
Python Deep Learning Projects
Matthew Lamons | Rahul Kumar | Abhishek Nagaraja
Oct, 2018 | 472 pages
Small book image
Python Deep Learning Cookbook
Indra den Bakker
Oct, 2017 | 330 pages
Small book image
Neural Networks with Keras Cookbook
V Kishore Ayyadevara
Feb, 2019 | 568 pages
Small book image
Deep Learning with R Cookbook
Swarna Gupta | Rehan Ali Ansari | Dipayan Sarkar
Feb, 2020 | 328 pages
Table of Contents (17 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
Building Deep Learning Environments
Building Deep Learning Environments
Building a common DL environment
DL environment setup locally
Setting up a DL environment in the cloud
Cloud platforms for deployment
Automating the setup process
Summary
2
Training NN for Prediction Using Regression
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
Let's code the implementation!
Concluding the project
Summary
3
Word Representation Using word2vec
Word Representation Using word2vec
Learning word vectors
Visualizing the embedding space by plotting the model on TensorBoard
Building language models using CNN and word2vec
Summary
4
Building an NLP Pipeline for Building Chatbots
Building an NLP Pipeline for Building Chatbots
Basics of NLP pipelines
Building conversational bots
Serving chatbots
Summary
5
Sequence-to-Sequence Models for Building Chatbots
Sequence-to-Sequence Models for Building Chatbots
Introducing RNNs
Implementing basic RNNs
LSTM architecture
Implementing an LSTM model
Sequence-to-sequence models
Summary
6
Generative Language Model for Content Creation
Generative Language Model for Content Creation
LSTM for text generation
Generating lyrics using deep (multi-layer) LSTM
Generating music using a multi-layer LSTM
Summary
7
Building Speech Recognition with DeepSpeech2
Building Speech Recognition with DeepSpeech2
Data preprocessing
DS2 model description and intuition
Training the model
Testing and evaluating the model
Summary
8
Handwritten Digits Classification Using ConvNets
Handwritten Digits Classification Using ConvNets
Code implementation
Conclusion
Summary
9
Object Detection Using OpenCV and TensorFlow
Object Detection Using OpenCV and TensorFlow
Object detection intuition
Object detection using OpenCV
Object detection using deep learning
Image segmentation
Conclusion
Summary
10
Building Face Recognition Using FaceNet
Building Face Recognition Using FaceNet
Setup environment
Building the pipeline
Preprocessing of images
Training the classifier
Evaluation
Summary
11
Automated Image Captioning
Automated Image Captioning
Data preparation
Defining the captioning model
Training the captioning model
Evaluating the captioning model
Deploying the captioning model
Summary
12
Pose Estimation on 3D models Using ConvNets
Pose Estimation on 3D models Using ConvNets
Code implementation
Importing the dependencies
Conclusion
Summary
13
Image Translation Using GANs for Style Transfer
Image Translation Using GANs for Style Transfer
Let's code the implementation!
The conclusion to the project
Summary
14
Develop an Autonomous Agent with Deep R Learning
Develop an Autonomous Agent with Deep R Learning
Let's get to the code!
Deep Q-learning
Deep SARSA learning
The conclusion to the project
Summary
15
Summary and Next Steps in Your Deep Learning Career
Summary and Next Steps in Your Deep Learning Career
Python deep learning – building the foundation – two projects
Python deep learning – NLP – 5 projects
Deep learning – computer vision – 6 projects
Python deep learning – autonomous agents – 1 project
Next steps – AI strategy and platforms
Conclusion and thank you!
16
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Training the captioning model

Now, let's train the model. The first thing we need to do is to extract the features stored in the respective .npy files and then pass those features through the CNN encoder.

The encoder output, hidden state (initialized to 0) and the decoder input (which is the start token) are passed to the decoder. The decoder returns the predictions and the decoder hidden state.

The decoder hidden state is then passed back into the model and the predictions are used to calculate the loss. While training, we use the teacher forcing technique to decide the next input to the decoder.

Teacher forcing is the technique where the target word is passed as the next input to the decoder. This technique helps to learn the correct sequence or correct statistical properties for the sequence, quickly.

The final step is to calculate the gradient and apply it to the optimizer...

Previous Section
End of Section 4
Next Section