Repository files navigation

This repository contains material related to Udacity'sDeep Learning v7 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.

• Introduction to Neural Networks: Learn how to implement gradient descent and apply it to predicting patterns in student admissions data.
• Sentiment Analysis with NumPy:Andrew Trask leads you through building a sentiment analysis model, predicting if some text is positive or negative.
• Introduction to PyTorch: Learn how to build neural networks in PyTorch and use pre-trained networks for state-of-the-art image classifiers.

• Convolutional Neural Networks: Visualize the output of layers that make up a CNN. Learn how to define and train a CNN for classifyingMNIST 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 theCIFAR10 dataset.
• Transfer Learning. In practice, most people don't train their own networks on huge datasets; they usepre-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!

• 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 to 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 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.

• All exercise and project notebooks for the lessons on model deployment can be found in the linked, Github repo. Learn to deploy pre-trained models using AWS SageMaker.

• 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.

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

Per the Anacondadocs:

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

Using Anaconda consists of the following:

1. Installminiconda on your computer, by selecting the latest Python version for your operating system. If you already haveconda orminiconda installed, you should be able to skip this step and move on to step 2.
2. Create and activate * a newcondaenvironment.

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

Download the latest version ofminiconda that matches your system.

Installminiconda on your machine. Detailed instructions:

• Linux:https://conda.io/projects/conda/en/latest/user-guide/install/linux.html
• Mac:https://conda.io/projects/conda/en/latest/user-guide/install/macos.html
• Windows:https://conda.io/projects/conda/en/latest/user-guide/install/windows.html

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

These instructions also assume you havegit 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 usinggit from the command line, take a look at ourfree 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.gitcd deep-learning-v2-pytorch

2. Create (and activate) a new environment, nameddeep-learning with Python 3.6. If prompted to proceed with the install(Proceed [y]/n) type y.

   • Linux orMac:

   conda create -n deep-learning python=3.6source activate deep-learning

   • Windows:

   conda create --name deep-learning python=3.6activate 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.

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

   • Linux orMac:

   conda install pytorch torchvision -c pytorch

   • Windows:

   conda install pytorch -c pytorchpip install torchvision

4. Install a few required pip packages, which are specified in the requirements text file (including OpenCV).

pip install -r requirements.txt

7. That's it!

Now most of thedeep-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 yourdeep-learning environment is still activated, you can navigate to the main repo and start looking at the notebooks:

cdcd deep-learning-v2-pytorchjupyter notebook

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