Repo for the Deep Learning Nanodegree Foundations program.
Luke Rucks 55fcbcc0a2 Change wording in learning rate starting point explanation to reflect project update 1 year ago
autoencoder stride reduces the size by a factor 1 year ago
batch-norm Fix some typos 1 year ago
dcgan-svhn Fix overwritten parameter in GAN network 1 year ago
embeddings Update Skip-Gram_word2vec.ipynb 1 year ago
environments Fix tornado version in Mac environments 1 year ago
face_generation Update dlnd_face_generation.ipynb 1 year ago
first-neural-network Change wording in learning rate starting point explanation to reflect project update 1 year ago
gan_mnist GAN_mnist: fix `generator` return doc 1 year ago
image-classification Update FloydHub information for image classification project 1 year ago
intro-to-rnns Keep vocab mapping stable 1 year ago
intro-to-tensorflow fixed solutions github url 1 year ago
intro-to-tflearn Fix `trainY` and `testY` 1 year ago
language-translation Merge pull request #134 from JackBurdick/patch-1 1 year ago
reinforcement Remove training output from notebooks to make the files smaller. 1 year ago
semi-supervised Add semi-supervised notebooks 1 year ago
sentiment-network Simplify log ratios in Trask notebooks 1 year ago
sentiment-rnn Sentiment-RNN: Fixed Embedding size 1 year ago
seq2seq Fix dynamic_decode function to work with TensorFlow 1.2 1 year ago
tensorboard Remove spaces from filenames 1 year ago
transfer-learning don't ask to clone machrisaa/tensorflow-vgg 1 year ago
tv-script-generation docs: fixes spelling of "forms" to "forums" 1 year ago
weight-initialization add dependencies for weight initialization lesson. 1 year ago
.gitignore Merge branch 'master' into patch-1 1 year ago
.gitmodules Add gym as submodule 1 year ago
LICENSE Add LICENSE file 1 year ago Flesh out README 1 year ago

Deep Learning Nanodegree Foundation

This repository contains material related to Udacity’s Deep Learning Nanodegree Foundation 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 intialization and batch normalization.

There are also notebooks used as projects for the Nanodegree program. In the program itself, the projects are reviewed by Udacity experts, but they are available here as well.

Table Of Contents



  • Your First Neural Network: Implement a neural network in Numpy to predict bike rentals.
  • Image classification: Build a convolutional neural network with TensorFlow to classify CIFAR-10 images.
  • Text Generation: Train a recurrent neural network on scripts from The Simpson’s (copyright Fox) to generate new scripts.
  • Machine Translation: Train a sequence to sequence network for English to French translation (on a simple dataset)
  • Face Generation: Use a DCGAN on the CelebA dataset to generate images of novel and realistic human faces.


Each directory has a requirements.txt describing the minimal dependencies required to run the notebooks in that directory.


To install these dependencies with pip, you can issue pip3 install -r requirements.txt.

Conda Environments

You can find Conda environment files for the Deep Learning program in the environments folder. Note that environment files are platform dependent. Versions with tensorflow-gpu are labeled in the filename with “GPU”.