Skip to content
Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
attention Attention basics Oct 16, 2018
autoencoder data handling Sep 25, 2018
batch-norm fix typo Nov 19, 2018
convolutional-neural-networks Merge pull request #60 from AllanHasegawa/fix/crash_when_batch_size_u… Feb 18, 2019
cycle-gan Create samples directory Nov 11, 2018
dcgan-svhn
gan-mnist mnist GAN notebooks Nov 11, 2018
intro-neural-networks alt solution to one hot encoding Feb 26, 2019
intro-to-pytorch Merge pull request #89 from marielen/doc Jan 28, 2019
keras keras exercises and examples Sep 25, 2018
project-bikesharing Fixes Issue #136 Feb 10, 2019
project-dog-classification Added support for truncated images Feb 12, 2019
project-face-generation face generation project Nov 11, 2018
project-tv-script-generation Corrected comments describing parameters #124 Jan 24, 2019
recurrent-neural-networks Fix minor typos in char rnn notebooks Feb 17, 2019
sentiment-analysis-network
sentiment-rnn Merge pull request #96 from Fernandohf/bugFix-RuntimeError Jan 28, 2019
style-transfer Merge pull request #85 from GabrielePicco/chapther6AllowLoadFromURL Feb 18, 2019
tensorflow/intro-to-tensorflow
transfer-learning Added torch.nn import Feb 18, 2019
weight-initialization fix link Nov 5, 2018
word2vec-embeddings SkipGram Word2Vec implementation Oct 16, 2018
.gitignore update gitignore Nov 13, 2018
LICENSE Initial commit Sep 4, 2018
README.md
requirements.txt Update reqs Sep 4, 2018

README.md

Deep Learning (PyTorch)

This repository contains material related to Udacity's Deep Learning Nanodegree program. It consists of a bunch of tutorial notebooks for various deep learning topics. In most cases, the notebooks lead you through implementing models such as convolutional networks, recurrent networks, and GANs. There are other topics covered such as weight initialization and batch normalization.

There are also notebooks used as projects for the Nanodegree program. In the program itself, the projects are reviewed by real people (Udacity reviewers), but the starting code is available here, as well.

Table Of Contents

Tutorials

Introduction to Neural Networks

Convolutional Neural Networks

  • Convolutional Neural Networks: Visualize the output of layers that make up a CNN. Learn how to define and train a CNN for classifying MNIST data, a handwritten digit database that is notorious in the fields of machine and deep learning. Also, define and train a CNN for classifying images in the CIFAR10 dataset.
  • Transfer Learning. In practice, most people don't train their own networks on huge datasets; they use pre-trained networks such as VGGnet. Here you'll use VGGnet to help classify images of flowers without training an end-to-end network from scratch.
  • Weight Initialization: Explore how initializing network weights affects performance.
  • Autoencoders: Build models for image compression and de-noising, using feedforward and convolutional networks in PyTorch.
  • Style Transfer: Extract style and content features from images, using a pre-trained network. Implement style transfer according to the paper, Image Style Transfer Using Convolutional Neural Networks by Gatys et. al. Define appropriate losses for iteratively creating a target, style-transferred image of your own design!

Recurrent Neural Networks

  • Intro to Recurrent Networks (Time series & Character-level RNN): Recurrent neural networks are able to use information about the sequence of data, such as the sequence of characters in text; learn how tom implement these in PyTorch for a variety of tasks.
  • Embeddings (Word2Vec): Implement the Word2Vec model to find semantic representations of words for use in natural language processing.
  • Sentiment Analysis RNN: Implement a recurrent neural network that can predict if the text of a moview review is positive or negative.
  • Attention: Implement attention and apply it to annotation vectors.

Generative Adversarial Networks

  • Generative Adversarial Network on MNIST: Train a simple generative adversarial network on the MNIST dataset.
  • Batch Normalization: Learn how to improve training rates and network stability with batch normalizations.
  • Deep Convolutional GAN (DCGAN): Implement a DCGAN to generate new images based on the Street View House Numbers (SVHN) dataset.
  • CycleGAN: Implement a CycleGAN that is designed to learn from unpaired and unlabeled data; use trained generators to transform images from summer to winter and vice versa.

Deploying a Model (with AWS SageMaker)

Projects

  • Predicting Bike-Sharing Patterns: Implement a neural network in NumPy to predict bike rentals.
  • Dog Breed Classifier: Build a convolutional neural network with PyTorch to classify any image (even an image of a face) as a specific dog breed.
  • TV Script Generation: Train a recurrent neural network to generate scripts in the style of dialogue from Seinfeld.
  • Face Generation: Use a DCGAN on the CelebA dataset to generate images of new and realistic human faces.

Elective Material

  • Intro to TensorFlow: Starting building neural networks with TensorFlow.
  • Keras: Learn to build neural networks and convolutional neural networks with Keras.

Dependencies

Configure and Manage Your Environment with Anaconda

Per the Anaconda docs:

Conda is an open source package management system and environment management system for installing multiple versions of software packages and their dependencies and switching easily between them. It works on Linux, OS X and Windows, and was created for Python programs but can package and distribute any software.

Overview

Using Anaconda consists of the following:

  1. Install miniconda on your computer, by selecting the latest Python version for your operating system. If you already have conda or miniconda installed, you should be able to skip this step and move on to step 2.
  2. Create and activate * a new conda environment.

* Each time you wish to work on any exercises, activate your conda environment!


1. Installation

Download the latest version of miniconda that matches your system.

Linux Mac Windows
64-bit 64-bit (bash installer) 64-bit (bash installer) 64-bit (exe installer)
32-bit 32-bit (bash installer) 32-bit (exe installer)

Install miniconda on your machine. Detailed instructions:

2. Create and Activate the Environment

For Windows users, these following commands need to be executed from the Anaconda prompt as opposed to a Windows terminal window. For Mac, a normal terminal window will work.

Git and version control

These instructions also assume you have git installed for working with Github from a terminal window, but if you do not, you can download that first with the command:

conda install git

If you'd like to learn more about version control and using git from the command line, take a look at our free course: Version Control with Git.

Now, we're ready to create our local environment!

  1. Clone the repository, and navigate to the downloaded folder. This may take a minute or two to clone due to the included image data.
git clone https://github.com/udacity/deep-learning-v2-pytorch.git
cd deep-learning-v2-pytorch
  1. Create (and activate) a new environment, named deep-learning with Python 3.6. If prompted to proceed with the install (Proceed [y]/n) type y.

    • Linux or Mac:
    conda create -n deep-learning python=3.6
    source activate deep-learning
    
    • Windows:
    conda create --name deep-learning python=3.6
    activate deep-learning
    

    At this point your command line should look something like: (deep-learning) <User>:deep-learning-v2-pytorch <user>$. The (deep-learning) indicates that your environment has been activated, and you can proceed with further package installations.

  2. Install PyTorch and torchvision; this should install the latest version of PyTorch.

    • Linux or Mac:
    conda install pytorch torchvision -c pytorch 
    
    • Windows:
    conda install pytorch -c pytorch
    pip install torchvision
    
  3. Install a few required pip packages, which are specified in the requirements text file (including OpenCV).

pip install -r requirements.txt
  1. That's it!

Now most of the deep-learning libraries are available to you. Very occasionally, you will see a repository with an addition requirements file, which exists should you want to use TensorFlow and Keras, for example. In this case, you're encouraged to install another library to your existing environment, or create a new environment for a specific project.

Now, assuming your deep-learning environment is still activated, you can navigate to the main repo and start looking at the notebooks:

cd
cd deep-learning-v2-pytorch
jupyter notebook

To exit the environment when you have completed your work session, simply close the terminal window.

You can’t perform that action at this time.