dholdaway / deep-learning-with-python-notebooks

Jupyter notebooks for the code samples of the book "Deep Learning with Python"

Companion Jupyter notebooks for the book "Deep Learning with Python"

This repository contains Jupyter notebooks implementing the code samples found in the book Deep Learning with Python (Manning Publications). Note that the original text of the book features far more content than you will find in these notebooks, in particular further explanations and figures. Here we have only included the code samples themselves and immediately related surrounding comments.

These notebooks use Python 3.6 and Keras 2.0.8. They were generated on a p2.xlarge EC2 instance.

Table of contents

• Chapter 2:
  • 2.1: A first look at a neural network
• Chapter 3:
  • 3.5: Classifying movie reviews
  • 3.6: Classifying newswires
  • 3.7: Predicting house prices
• Chapter 4:
  • 4.4: Underfitting and overfitting
• Chapter 5:
  • 5.1: Introduction to convnets
  • 5.2: Using convnets with small datasets
  • 5.3: Using a pre-trained convnet
  • 5.4: Visualizing what convnets learn
• Chapter 6:
  • 6.1: One-hot encoding of words or characters
  • 6.1: Using word embeddings
  • 6.2: Understanding RNNs
  • 6.3: Advanced usage of RNNs
  • 6.4: Sequence processing with convnets
• Chapter 8:
  • 8.1: Text generation with LSTM
  • 8.2: Deep dream
  • 8.3: Neural style transfer
  • 8.4: Generating images with VAEs
  • 8.5: Introduction to GANs

Run on FloydHub

You can easily run these code samples on GPU-powered Jupyter notebooks with FloydHub. Install the floyd-cli command line tool and run these commands to get started:

# Create a new folder for the project
mkdir deep-learning
cd deep-learning

# Clone the existing project from FloydHub
floyd clone redeipirati/projects/deep-learning-with-python-notebooks/25

# Initialize the project folder
floyd init deep-learning

# Run an interactive GPU instance with everything you need
floyd run \
  --env tensorflow-1.4 \
  --data redeipirati/datasets/cats_and_dogs_small/1:input \
  --mode jupyter \
  --gpu