UdacityDeepLearningPyTorch

Exercises and projects given in the Deep Learning ND program offered by Udacity.com.

Overview

The following topics will be addressed:

the concept of tensors which is the main data structure of PyTorch and how tensors interact with NumPy Python package.
the PyTorch module named autograd to calculate gradients for training neural networks. It is able to perform backpropagation by calculating the gradients at each operation in the network
we will build a neural network and do the forward propagation
we will define a loss and an optimization method to train a neural neywork (on a dataset of handwritten digits)
we will understand how to test how a neural network is able to generalize using the validation procedure
we will see that your neural network is not able to work well with more complex images, so we will learn a technique named transfer learning: to use pre-trained networks to improve the performances of your classifier

Name		Name	Last commit message	Last commit date
Latest commit History 8 Commits
.vscode		.vscode
MNIST/raw		MNIST/raw
.gitignore		.gitignore
LICENSE		LICENSE
Part 1 - RNN Time Series.ipynb		Part 1 - RNN Time Series.ipynb
Part 1 - Tensors in PyTorch.ipynb		Part 1 - Tensors in PyTorch.ipynb
Part 2 - Neural Networks in PyTorch.ipynb		Part 2 - Neural Networks in PyTorch.ipynb
Part 2 - RNN Character Level.ipynb		Part 2 - RNN Character Level.ipynb
Part 3 - Training a Neural Network.ipynb		Part 3 - Training a Neural Network.ipynb
Part 4 - Faschion-MNIST.ipynb		Part 4 - Faschion-MNIST.ipynb
Part 5 - Inference and Validation.ipynb		Part 5 - Inference and Validation.ipynb
Part 6 - Saving and Loading Models.ipynb		Part 6 - Saving and Loading Models.ipynb
Part 7 - Loading Image Data.ipynb		Part 7 - Loading Image Data.ipynb
Part 8 - Transfer Learning.ipynb		Part 8 - Transfer Learning.ipynb
README.md		README.md
fc_model.py		fc_model.py
helper.py		helper.py